时间		会议安排	地点	主持人
2023.8.25	9:30-12:00	HHME 2023 Tutorials - 普适计算（PCC）Session1 李   桐：清华大学 卢   立：浙江大学 刘思聪 西北工业大学	411会议室	陈龙彪（厦门大学）
	14:00-17:30	HHME 2023 Tutorials - 普适计算（PCC）Session2 鲁剑锋：武汉科技大学 惠   维：西安交通大学 古富强：重庆大学	411会议室	赵   莎（浙江大学）
	18:30-21:30	PCC普适计算专委换届	405会议室	谢   磊（南京大学）
2023.8.26	14:00-16:00	PCC青年学者论坛1：泛在智能感知 靳战鹏：华南理工大学 王   柱：西北工业大学 邹永攀:深圳大学 王楚豫:南京大学 刘   璇:湖南大学	410/412会议室	谢   磊（南京大学） 王乐业（北京大学）
	16:00-18:00	PCC青年学者论坛2:泛在数据分析 赵   莎:浙江大学 王晋东:微软亚洲研究院 梁宇轩:香港科技大学（广州） 王乐业:北京大学
	14:00-17:00	PCC论文交流论坛1	407会议室	陈   超（重庆大学）
	14:00-17:00	PCC论文交流论坛2	408会议室	李   桐（清华大学）
2023.8.27	11:10-12:10	PCC论坛：普适计算与人工智能的融合之路 贾维嘉、房鼎益、金蓓弘、郭斌、王亚沙、赵蕴龙	410/412会议室	谢   幸（微软亚洲研究院）
	14:00-18:00	PCC顶会顶刊论文交流论坛1	407报告厅	张扶桑（中国科学院软件所）
		PCC顶会顶刊论文交流论坛2	408报告厅	刘志丹（深圳大学）
		PCC论文交流论坛3	409报告厅	赵   莎（浙江大学）
		PCC论文交流论坛4	411报告厅	汪   磊（苏州大学）

HHME 2023 Tutorials - 普适计算（PCC）

人员简介
论坛主席一：陈龙彪 副教授 厦门大学	个人简介： 厦门大学南强青年拔尖人才计划研究员、信息学院副教授，福建省高层次引进人才、厦门市高层次留学人才。主要研究方向为群智感知、空间计算、普适计算。连续两次以第一作者获得CCF-A类会议UbiComp最佳论文提名奖（国内高校首次），荣获2022年度ACM SIGSPATIAL中国分会新星奖（本年度全国唯一）。累计发表论文50篇，担任ACM中国SIGSPATIAL分会执行委员、CCF普适计算专委会执行委员、CCF YOCSEF厦门分论坛主席、CCF高级会员、金砖国家青年科学家论坛成员。担任ACM UbiComp 2021社会活动主席，担任AAAI, IJCAI等国际会议程序委员会委员，以及FSC, Vehicles等国际期刊编委。-IEEE CS青年科学家奖(2016)、IEEE TCSC Award for Excellence (Middle Career Researcher, 2018)，入选2016年中国高等学校十大科技进展、2020年世界互联网领先科技成果。指导学生获CCF-A类国际会议的最佳论文奖、最佳论文提名奖多次。目前担任IEEE Trans. Neural Networks and Learning Systems、IEEE Trans. Cognitive and Developmental Systems等多个国际期刊编委。
论坛主席二：赵   莎 研究员 浙江大学	个人简介： 浙江大学计算机学院特聘研究员，博士生导师。2017年06月于浙江大学计算机学院获得博士学位，期间访问卡耐基梅隆大学，2017至2020年在浙江大学计算机学院从事博士后研究。研究方向为智能感知，脑机接口。发表论文40余篇，获得ACM UbiComp 2016最佳论文奖 (国内首篇)，并荣获2022年ACM杭州新星奖。主持国自然青基、2030“脑科学与类脑研究”重大项目子课题，重点研发计划子课题等。担任CCF普适专委委员，ACM杭州分会主席团成员，CCF 高级会员，担任AAAI，IJCAI等会议程序委员会委员，以及UbiComp等国际顶级会议与期刊的审稿人。
特邀讲者一：李   桐	讲者简介： 清华大学电子工程系助理研究员。2021年于香港科技大学获计算机科学与工程博士学位。主要研究方向为无线网络孪生、网络模拟与决策、城市计算。在Nature Sustainability, KDD, WWW, TMC, TKDE等期刊及会议上发表论文40余篇。曾获博士后国际交流计划引进项目，中国博士后科学基金面上资助，芬兰诺基亚基金会资助，国家优秀自费留学生奖学金。担任KDD，ICC，AAAI，IJCAI，ECAI等会议程序委员会委员。 报告题目：基于生成式AI的城市模拟器 报告摘要： 在城市快速发展的过程中，各地都在探索运用现代化的信息技术手段来解决产生的问题和挑战。然而，目前已有的解决方案主要集中在信息整合和数据分析方面，无法满足城市治理中最关键的决策需求。具体而言，目前缺乏对决策效果的验证基础，也缺乏能够持续高效优化决策的解决方案。这些问题给城市治理带来了全新的挑战。城市孪生模拟引擎可以基于城市信息化基础设施所感知到的数据，对城市进行镜像建模，还原城市的历史运行情况，并预测未来的发展趋势。因此，城市孪生引擎为城市治理提供了一个决策验证的平台。本报告将主要讨论如何利用人工智能生成算法实现智能城市模拟。通过利用大规模城市感知数据和数据与知识联合驱动的生成算法，我们可以对城市复杂的交通和人流系统进行智能模拟。基于建立模拟的孪生人流系统，进一步建立城市复杂系统的基础模型，模拟城市的物理和社会功能要素之间的时空关系和流通网络，包括建筑、道路、人员、车辆、通信、电力、交通和供水等。城市孪生模拟平台可以全面分析和优化城市系统的各个方面，包括交通流量、通信网络、基础设施规划、公共交通规划等，为合理规划城市生产、生活和生态空间提供基础性智能平台，为政府、企业部门的决策与政策制定提供数据与平台支撑。
特邀讲者二：卢   立	讲者简介： 浙江大学计算机科学与技术学院-网络空间安全学院特聘研究员、博导。分别于上海交通大学、西安交通大学获博士、双学士学位。曾获国家留学基金委资助访问美国罗格斯大学。研究工作主要集中在智能物联网安全、语音对抗攻防、移动感知、普适计算等方面，在USENIX Security、UbiComp、SenSys等国际一流期刊与会议上发表40余篇论文。获MobiCom 2019与2022年最佳海报展示提名奖，ACM中国分会优秀博士学位论文奖，上海市计算机学会优秀博士学位论文提名奖等荣誉。担任CCF会普适计算专委会执行委员，浙江省网络空间安全协会专技委副秘书长。担任IEEE INFOCOM, IEEE ICDCS, IEEE/ACM IWQoS等会议的程序委员会委员。 报告题目：智能语音系统安全 报告摘要： 智能语音系统近年来在个人语音助手、智能音箱、自然身份识别等领域得到广泛应用。语音下天然内嵌有文本内容与声纹两大类信息，能够提供更接近人类交互的用户体验。通过灵活应用语音下的信息，当前系统已在智能座舱、移动银行、个性化服务等场景下大放异彩。然而，与其他基于深度学习的系统相似，其同样笼罩在近年来受到广泛研究的对抗样本、模型后门、深度伪造等低成本攻击的阴影之下。本报告主要分享我们围绕智能语音系统的一些对抗样本攻防探索，并围绕传统语音加性扰动的劣势，介绍一种基于语音混响失真研发的新型对抗样本工具，从对抗样本攻击、模型后门等方面展开的一系列攻击研究。最后，本报告还将分享该新型工具在用户身份隐私保护的应用研究，探索攻击技术工具在正面场景中的应用可能。
特邀讲者三：刘思聪	讲者简介： 工学博士，西北工业大学计算机学院副教授，入选中国科协未来女科学家计划。研究方向为普适计算、移动嵌入式智能、智能物联网。在ACM MobiSys、ACM Ubicomp等高水平会议/期刊上发表论文30余篇，授权专利6项，出版《人机物融合群智计算》《智能物联网导论》专著/教材2部；曾获ACM SIGBED中国优博、CCF推荐A类会议ACM UbiComp“杰出论文奖”、陕西高等学校科学技术特等奖、一等奖等奖项；担任Applied Science客座编委、IEEE AIoTSys、Metaverse2023国际会议程序副主席、CCF普适计算专委会委员、ACM SIGBED China青年委员、ACM MobiSys 2021、2023 TPC、以及IEEE TMC、ACM IMWUT、CHI等国际顶级会议/期刊审稿人。 报告题目：智能物联网边端自适应深度计算 报告摘要： 近年来人机物三元融合计算成为重要趋势，具有感知、计算和移动能力的移动嵌入式设备（如智能手机、无人机、机器人等）逐渐成为其重要组成，并融入智能制造、智慧城市等国家重大应用领域。此外，边缘智能将计算推向移动嵌入式边端，可进一步提升系统高效性、隐私性和可靠性。如何面向边端计算资源的异质、受限和动态性特点，以及应用系统的高响应与可靠性需求，实现边端计算的自适应优化与运行时演化成为一个关键问题。本次报告将介绍边端情境自适应深度计算与演化的研究背景、挑战、研究实践和展望。
特邀讲者四：鲁剑锋	讲者简介： 武汉科技大学三级教授、博导、研究生院副院长、湖北省“楚天学者”特聘教授、浙江省杰出青年基金获得者。是CCF物联网/普适计算专委会执行委员、国家重点研发计划“物联网与智慧城市”重点专项答辩评审专家、湖北省/浙江省/广东省科技计划项目评审专家等。主要研究兴趣包括群智感知、联邦学习、博弈论及其应用等。近年来以第一作者/通讯作者在JSAC、TIFS、TOIT、TII、TVT、TCSS等有影响力国际期刊及会议上发表论文40余篇。先后主持国家自然科学基金4项、省部级课题6项。 报告题目：群智计算在线激励与公平优化 报告摘要： 传统物联网感知范式 “以物为中心”，存在可扩展性弱、维护成本高、覆盖范围滞、数据类型少等问题。相比之下，群智计算 “以人为中心”，正好弥补传统感知四方面不足，目前已成为一种新型的物联网感知范式。然而，在群智计算中，如何充分利用参与者资源，优化任务分配方案，提高系统整体效用是当前一个亟需解决的重要问题。本报告将介绍如何针对在线型群智任务不断涌现而参与者资源相对有限且分布不均这一现实困境，从寻求系统效益和社会公平最优平衡视角出发，充分借鉴博弈论策略思维，采用最优化理论、李雅普诺夫优化、近似算法、机器学习等多学科交叉知识融会贯通，研究多群智任务在线激励与公平优化理论和方法，为促进群智计算的可持续性健康发展提供新的思路和方法。
特邀讲者五：惠   维	讲者简介： 西安交通大学计算机学院教授、博士生导师、ACM西安分会副秘书长、人机混合增强智能全国重点实验室智能感知中心副主任、西安市大数据与人工智能重点实验室副主任，主持国家重点研发计划课题、国家自然科学基金等科研项目10余项，发表学术论文100余篇，其中CCF A类论文40余篇，谷歌引用3300余次，获CCF A类会议IEEE INFOCOM 2019大会最佳论文奖、2022年教育部自然科学一等奖（排名2）、2023年陕西高等学校科学技术研究优秀成果一等奖（排名1）。 报告题目：工业物联网智能感知与可信计算 报告摘要： 通过物联网与人工智能技术深度结合，实现“人、机、物”高效互联互通，是近年来工业物联网技术发展的趋势，也是我国制造业智能化改造升级的重要手段。面向工业应用实际，聚焦物联网技术科学前沿，针对感知分辨率不足、传输兼容性不强、认证可信度不高三方面战，研究基于反向散射信号的超分辨率感知增强技术、基于载波复用的跨协议并发高效传输技术、基于异构数据多级融合的可信身份认证技术，促进物联网、网络安全和工业领域的深度融合与落地应用。
特邀讲者六：古富强	讲者简介： 重庆大学计算机学院教授、博士/硕士生导师，澳大利亚墨尔本大学博士，入选重庆市高层次人才计划。曾先后在德国亚琛工业大学、加拿大多伦多大学、新加坡国立大学从事研究工作。研究方向包括（但不局限于）导航定位与机器人等。在IEEE TMC、TVT、TIM、ACM Computing Surveys、IEEE Sensors、RA-L、IJGIS、ISPRS J、IJCAI、ICRA、GLOBECOM、IROS等国际主流期刊及会议发表论文50余篇；主持了军科委重大项目课题、国家自然科学基金面上项目、之江实验室开放基金、重庆市留创计划项目等；担任了IEEE Sensors Journal、Frontiers in Robotics and AI等SCI期刊副主编、《导航定位与授时》期刊青年编委以及IPIN 2022/2023、UPINLBS 2022、iThings 2022、ICGNC 2022等国际会议分会主席。 报告题目：面向复杂场景的导航定位技术 报告摘要： 目前，全球卫星定位系统随已广泛应用于各行各业，但其在复杂场景（例如商场、机场）下由于卫星信号受到遮挡而无法适用。面向复杂场景的导航定位技术已成为近年来的一个研究热点。本报告将首先介绍当前主流的面向复杂场景的导航定位技术和算法，包括无线定位、航位推算、视觉定位等；然后介绍如何将主流的深度学习算法（例如自编码解码器、卷积神经网络、LSTM等）与这些定位感知算法相结合；最后，展望定位感知技术的未来发展趋势。

PCC青年学者论坛

人员简介
论坛主席一：谢   磊	个人简介： 谢磊，南京大学计算机科学与技术系副主任，教授，博士生导师，入选“教育部青年长江学者”，工业互联网战略咨询专家委员会委员，CCF杰出会员，CCF杰出演讲者。担任中国计算机学会普适计算专委会秘书长、南京大学-南方电网数字平台工业互联网联合实验室主任。曾获江苏省科学技术奖一等奖、高等教育（本科）国家级教学成果奖一等奖、江苏省教学成果奖（高等教育类）特等奖、高校计算机专业优秀教师奖励计划、江苏省六大人才高峰创新人才团队、江苏省优秀博士学位论文、南京大学五四青年奖章、国际会议MobiQuitous最佳论文奖、国际期刊TPDS的SpotlightPaper等荣誉称号。主要研究领域为智能感知与边缘智能，目前共发表论文100余篇，包括国际一流学术会议ACM MOBICOM、ACM UBICOMP、IEEE INFOCOM，国际一流学术期刊ACM/IEEE TON、IEEE TMC等。
论坛主席二：王乐业	个人简介： 北京大学计算机学院、高可信软件技术教育部重点实验室研究员，入选国家级青年人才计划。长期从事隐私保护下的泛在数据采集、挖掘、共享等相关研究，成果应用于群智感知、城市交通、医疗健康等数据智能场景。发表国际会议、期刊论文70余篇，累计引用5500余次。成果获普适计算顶会UbiComp最佳论文提名奖，人工智能顶刊Artificial Intelligence亮点论文等奖项。
PCC青年学者论坛1：泛在智能感知
靳战鹏	讲者简介： 华南理工大学长聘教授、信实冠名教授、博士生导师，人体数据感知教育部工程研究中心副主任，广东省数字孪生人重点实验室副主任。曾任纽约州立大学布法罗分校计算机科学与工程系终身制副教授，研究生部主任，Cyber-Med实验室主任。ACM和IEEE高级会员。目前主要研究兴趣包括普适计算，人机交互，智能感知，主动健康，人工智能以及相关技术在智慧医疗、生物特征识别、及物联网领域的应用。曾任美国空军研究院（AFRL）访问学者，美国国家科学基金会（NSF）、美国国家标准与技术研究院（NIST），美国陆军研究办公室（ARO）等机构的项目评审专家。目前担任四个国际期刊的副主编（ACM Computing Surveys, ACM IMWUT, Elsevier Computers in Biology and Medicine, CCF TPCI）和30余个国际期刊和会议的审稿人或技术委员会委员。已发表论文100余篇，其中主要工作发表在ACM IMWUT/UbiComp、ACM Computing Surveys， IEEE TIFS、TMC、TIM、TBME等期刊。 报告题目：可听计算：从普适感知到智能交互 报告摘要： 近年来伴随着可穿戴技术的发展和新的使用场景的大量出现，无线耳机成为继智能手机，智能手表之后的下一代个人可穿戴交互平台。在人工智能技术的推动下，耳机已不再仅仅是用来听音乐打电话的设备，而成为可以实现语音助理，智能人机交互，甚至疾病健康监测的智能平台，其巨大的应用潜力和发展空间形成了一个新的研究领域―可听计算（Hearable Computing）。围绕这一方向，我们进行了一系列的科研探索。首先，利用多模态声学传感技术实现了基于耳机的主动和被动安全认证。通过对人体耳道生理结构和声学特性的研究，利用每个个体内耳道声音传播，反射，吸收的独特信号频谱特性来作为标志个体的生物特征。此外，利用不同疾病和听力等级状态对于耳道物理和生理上的改变，将耳机转型成为一种有效、方便、低价、和易用的耳健康和普适听力检测方案。最后，基于多模态混合智能感知技术的智能人机交互研究，已经在手势识别和手语实时翻译、无声语音接口、和脸部表情识别上得到应用。
王   柱	讲者简介： 西北工业大学教授/博导，陕西省青年科技新星，主要从事智能无线感知与普适计算方面研究工作。先后主持国家自然科学基金面上、军科委创新特区课题、国家重大研发计划子课题等国家级项目，参与国家“973”计划课题、国家自然科学基金重点等国家级重点项目。在 IEEE TMC、IEEE TKDE、ACM UbiComp、IEEE ICDE等中国计算机学会（CCF）推荐期刊/会议上发表论文80余篇，Google学术引用4000余次；4篇论文入选ESI高被引论文，5篇论文获得领域国际知名学术会议最佳论文奖。受邀担任World Wide Web Journal、IEEE WoWMoM 2022等多个CCF推荐期刊/会议的客座编委/程序主席。曾获教育部高等学校科技进步一等奖1项、自然科学二等奖1项，陕西省科学技术一等奖1项。 报告题目：面向穿墙场景的Wi-Fi无线感知理论 报告摘要： 居家、办公等是无线感知的重要应用领域，穿墙感知是典型场景之一。现有工作主要从应用角度开展穿墙感知研究，较少关注穿墙无线感知的基础理论和模型。本报告从穿墙场景无线信号如何传播、感知能力如何变化等问题出发，构建了基于菲涅尔区模型的Wi-Fi穿墙感知理论，发现了由于空气与墙壁物理特性差异导致菲涅尔区出现“膨胀”和“压缩”效应，刻画了穿墙场景下Wi-Fi信号的感知能力和极限，形成了更具普适性的反射-折射一体化Wi-Fi感知菲涅尔区模型，为穿墙场景无线感知系统优化设计奠定了理论基础。
邹永攀	讲者简介： 博士，深圳大学计算机与软件学院长聘副教授，深圳市海外高层次人才，深圳大学荔园优青。2017年6月毕业于香港科技大学计算机系获博士学位。主要研究领域包括可穿戴/移动计算，普适计算和人机交互。已在ACM Mobicom、ACM Ubicomp、IEEE ICDCS 、IEEE Percom、IEEE TMC等国际学术会议和期刊上发表学术论文20余篇。曾获深圳市自然科学一等奖，IEEE MASS最佳论文奖，广东省计算机学会优秀论文一等奖，第二十三届中国专利优秀奖，第八届广东省专利优秀奖等。 报告题目：面向新型智能终端的感知与交互技术研究 报告摘要： 相比于传统智能设备，新型智能设备在形态、功能、尺型、硬件组成等方面具有独特属性。这既给用户情境信息的挖掘带来了机遇，也为面向新型设备交互技术带来了挑战。一方面，由于新型智能设备的类型和所内置传感器的种类要丰富得多，且其与用户更加切近能够获取到用户更为深层次的情境信息。因而，能够对用户多维度情境信息进行更细致、深入和全面的感知，从而对用户画像进行精准刻画。另一方面，由于新型智能设备形态和功能上差异，传统的触屏交互将变得低效且体验较差。因此，有必要研究面向新型智能终端的高效交互技术，主要解决装载传感器种类、数量的限制与交互需求之间的矛盾，以及算力、能量与实时精细交互之间的矛盾。
王楚豫	讲者简介： 博士，南京大学计算机科学与技术系特任副研究员，2018年10月于南京大学计算机科学与技术系获得博士学位。主要研究方向为“移动计算”与“智能感知计算”，目前在普适计算与移动计算研究领域共发表论文40余篇，包括国际一流学术期刊ACM/ IEEE TON、IEEE TMC，国际一流学术会议ACM UBICOMP、IEEE INFOCOM等。研究成果荣获获得IEEE INFOCOM 2018最佳演讲奖（Best-in-session Presentation Award）、MSLRA最佳workshop论文奖、HHME PCC会议最佳论文奖等。曾获得江苏省优秀博士论文奖，ACM中国优秀博士论文提名奖，ACM南京分会新星奖等。 报告题目：毫米波微状态感知初探 报告摘要： 近年来，随着物联网技术的飞速发展以及5G/6G场景下感传一体化的提出，使用无线信号进行目标感知已经得到学术界的广泛关注。毫米波雷达作为无线感知中的一类主要技术，因其灵敏度高、波长短、带宽大等优势被广泛研究使用。本次报告围绕声音、振动、呼吸、心跳等微状态感知问题，结合我们近年来的研究成果，从感知机理、模型构建以及目标优化等方面，介绍毫米波雷达在微状态感知方面的最新进展。我们力求通过充分挖掘信道之间的协同关联特性，来探索毫米波雷达的感知能力，拓展毫米波感知系统的应用场景。
刘   璇	讲者简介： 刘璇教授，博士生导师，湖南大学信息科学与工程学院院长助理。获评湖南省芙蓉学者青年学者，湖南省优青。主要从事物联网技术、智能感知等领域研究工作。相关研究工作发表于TMC、TPDS、TC、INFOCOM、Mobihoc、IJCAI等顶级国际期刊和会议，已发表/录用论文70多篇。主持和参与国家重点研发计划以及国家自然科学基金项目多项。担任多个国内外学术会议相关程序委员和组织委员会委员，以及IEEE/ACMTrans等多个国际期刊和会议审稿人。 报告题目：基于多智能体强化学习的群体智能协同策略 报告摘要： 群体智能作为新一代人工智能重点发展的五大智能形态之一，在民事和军事领域都具有重要的应用前景。如何提升智能个体的自组织、自学习能力，提升群智协同决策效率，是未来面向复杂任务实现群体智能的关键问题。近年来兴起的多智能体强化学习已成为解决复杂环境下决策控制问题的重要技术途径之一，在无人机群控制、智能交通系统、智能工业机器人等场景中被广泛应用。报告将根据策略的三类不同目标探讨目前基于多智能体深度强化学习的群智决策所面临的挑战，并介绍团队关于多智能体强化学习在复杂群智协同决策任务中的最新研究进展。
PCC青年学者论坛 2：泛在数据分析
赵   莎	讲者简介： 浙江大学计算机学院特聘研究员，博士生导师。2017年06月于浙江大学计算机学院获得博士学位，期间访问卡耐基梅隆大学，2017至2020年在浙江大学计算机学院从事博士后研究。研究方向为智能感知，脑机接口。发表论文40余篇，获得ACM UbiComp 2016最佳论文奖 (国内首篇)，并荣获2022年ACM杭州新星奖。主持国自然青基、2030“脑科学与类脑研究”重大项目子课题，重点研发计划子课题等。担任CCF普适专委委员，ACM杭州分会主席团成员，CCF 高级会员，担任AAAI，IJCAI等会议程序委员会委员，以及UbiComp等国际顶级会议与期刊的审稿人。 报告题目： 报告摘要：
王晋东	讲者简介： 微软亚洲研究院高级研究员、中科院计算所博士。研究兴趣为迁移学习、鲁棒机器学习、半监督学习及相关的视觉和普适计算等应用，近期主要关注大模型的鲁棒性和评测等问题。他在国际知名会议和期刊如NeurIPS、ICLR、CVPR、IJCAI、UbiComp、ACMMM、TKDE、TNNLS等发表50余篇论文，谷歌学术被引6000余次。获得IJCAI-19联邦学习研讨会最佳应用论文奖、清华大学AMiner 2012-2022十年最具影响力AI学者等荣誉奖项。出版的《迁移学习导论》一书帮助众多研究人员快速入门和学习该领域。领导开源了Github上最受欢迎的迁移学习项目（获得超1万星标）、半监督学习项目TorchSSL和USB、以及个性化联邦学习项目PersonalizedFL等。 报告题目：大模型时代的理论、评测与模型增强 报告摘要： 大型模型的日益普及丰富了我们的日常生活，但其稳健性仍然是一个紧迫且未触及的领域。为了让大型模型能够更好地适用于各种条件下，我们应该关注其限制和能力不足，即改善其稳健性。在本次演讲中，我们将从稳健性的角度介绍我们的一些工作，使机器学习模型在意外情况下更加稳健。具体而言，我们关注了三种情况：大模型Transformer架构的基础理论、模型评测、以及大模型的增强。
梁宇轩	讲者简介： 香港科技大学（广州）助理教授、博士生导师。于新加坡国立大学取得计算机科学博士学位，长期从事AI与数据科学技术在智慧城市、环境科学、智能交通等领域的跨学科交叉研究。在多个权威期刊和会议发表高水平论文40余篇（CCF A类论文达30余篇），包括TKDE、TMC、AI Journal、KDD、WWW、NeurIPS等。谷歌学术引用量2,400余次，h-index为22。曾获得新加坡数据科学联合会论文研究奖学金，新加坡国立大学院长博士生研究卓越奖，第二十三届中国专利优秀奖。 报告题目：当人工智能遇到时空数据：概念、方法和应用 报告摘要： 随着物联网、5G、移动互联网等新一代信息技术的快速发展，时空数据呈现爆发式增长。与图像、文本和语音数据相比，时空数据通常呈现出独特的时空特征，包括空间距离和层次性，以及时间接近性、周期性和趋势。时空人工智能是针对时空数据建模的专有人工智能技术，广泛用于交通、土木工程、环境、经济、生态和社会学等城市相关的交叉科学领域。本次讲座首先介绍时空人工智能的概念，从计算机科学的角度讨论其总体框架和主要挑战。其次，我们将时空人工智能的应用分为四类，分别是建模时空轨迹数据、时空网格数据、时空图数据和时空序列，以及各个类别中的代表性场景。我们之后重点描述了我们在上述四类数据的方法论上的最新探索和进展。最后，我们展望时空人工智能的未来，对未来有价值的研究方向进行了探讨。
王乐业	讲者简介： 北京大学计算机学院、高可信软件技术教育部重点实验室研究员，入选国家级青年人才计划。长期从事隐私保护下的泛在数据采集、挖掘、共享等相关研究，成果应用于群智感知、城市交通、医疗健康等数据智能场景。发表国际会议、期刊论文70余篇，累计引用5500余次。成果获普适计算顶会UbiComp最佳论文提名奖，人工智能顶刊Artificial Intelligence亮点论文等奖项。 报告题目：泛在数据分析的最小必要原则 报告摘要： 随物联网、移动计算等技术兴起，人机物融合的泛在感知计算已成为获取分析海量数据，助力城市建设、经济发展的核心手段之一。同时，数据治理法律法规体系日趋健全，而泛在感知数据涉及大量个体隐私和敏感信息，其安全治理刻不容缓。本报告将介绍面向泛在数据合规使用的最小必要原则及其在城市群智数据分析中的应用。具体围绕群智数据采集、融合、建模等各个阶段，展示实现数据最小必要原则的潜在方法。

PCC 论文交流论坛

Session 1：情景感知与群体智能（2023年8月26日）

报告题目：时空相关性条件下基于低预算实时预测的群智感知轨迹隐私保护方案 论坛讲者：蒋伟进, 王海娟, 周为, 陈艺琳, 吴玉庭, 韩裕清

报告题目：基于区块链的移动群智感知数据处理研究综述 论坛讲者：邵子豪, 霍如, 王志浩, 倪东, 谢人超

报告题目：基于遥感数据融合的热点检测研究 论坛讲者：李云倩, 翁丽娟, 王程, 陈超, 陈龙彪

报告题目：基于智能手机和声音信号的手势识别 论坛讲者：李朝辉, 蔡溢聪, 张永敏

报告题目：面向群体计算基于损失厌恶的激励机制 论坛讲者：井天琦, 李洋, 刘春颜, 赵蕴龙

报告题目：面向多目标状态感知的自适应云边协同调度研究 论坛讲者：周文晖, 彭清桦, 谢磊

报告题目：基于CrowdOS的群智机器人任务分配应用 论坛讲者：纪俊祥, 吴圣杰, 陈超, 王程, 陈龙彪

报告题目：面向移动目标感知的感通算一体化系统 论坛讲者：毛惠敏, 孙卓, 於志文, 郭斌

报告题目：面向复杂时序场景的无人机集群任务分配算法设计与实现 论坛讲者：侯李睿昭, 於志文, 骆艺轩, 崔禾磊, 郭斌

报告题目：基于商用WiFi设备的室内人数统计系统 论坛讲者：王炫之, 牛凯, 王俊喆, 姚智允, 余安澜, 张大庆

报告题目：基于OGC SWE框架和Handle标识技术的野外环境协同监测技术架构研究 论坛讲者：刘笑寒

报告题目：面向无人机协同定位应用的MCU深度计算编译优化 论坛讲者：熊康, 刘思聪, 郭斌, 於志文

报告题目：不确定环境下UAV-UGV空地协同搜索救援系统 论坛讲者：刘士琦, 郭斌, 赵凯星, 郝肇铁

报告题目：基于人机共融智能的众包机器学习研究 论坛讲者：王静宇, 王亮, 於志文, 王辉, 郭斌

报告题目：基于强化学习的园区服务机器人 论坛讲者：曾雯婷, 王妤妃, 陈超, 王程, 陈龙彪

报告题目：Push the Limit of Adversarial Example Attack on Speaker Recognition in Physical Domain 论坛讲者：陈钱牛, 陈锰, 卢立, 俞嘉地, Yingying Chen,王志波, 巴钟杰, 林峰, 任奎

报告题目：A Facial Key Point Offset Based Framework for Micro-Expression Recognition 论坛讲者：Mingzhong Wang, Qingshan Wang, Qi Wang, Zhiwen Zheng, Jiayu Li, Yuting Wang, Xinyang Ma, Yinjie Lu

报告题目：ContinuousSensing：A Task Allocation Algorithm for Human-Machine Collaborative Mobile Crowdsensing with Task Migration 论坛讲者：李浩洋, 於志文, 骆艺轩, 崔禾磊, 郭斌

Session 2：智慧医疗与社会计算（2023年8月26日）

报告题目：光CT时序状态多尺度预测方法研究 论坛讲者：郑贺源, 梁韵基, 严笑凯, 刘磊, 於志文

报告题目：基于气象因子的脑卒中发病预测模型研究 论坛讲者：王丁, 刘海明, 车啸平, 刘国强, 郭茜, 彭宇翔

报告题目：基于无线感知的多人呼吸检测方法 论坛讲者：雷杨倩, 王柱, 宋文超, 郭斌, 於志文

报告题目：基于LiDAR和UWB融合的移动场景呼吸感知研究 论坛讲者：苏玉琪, 兰自桐, 张扶桑, 金蓓弘

报告题目：眼底图像动脉-静脉分割的双注意力网络融合模型 论坛讲者：李欣平, 潘海为, 张可佳

报告题目：基于机器学习的重症循环衰竭预测因素 论坛讲者：薛莎莎, 张子昂, 张永敏

报告题目：基于细粒度急救需求预测的急救资源分配优化方法 论坛讲者：高鑫, 朱政烨, 吴仍裕, 周强, 赵俊峰, 王亚沙

报告题目：Mordo: 通过轻便的耳周生物传感器进行无声指令识别 论坛讲者：衣淳植, 魏柏淳, 朱剑飞, 姜峰, 陈志远, Seungmin Rho

报告题目：虚拟现实环境下用户导引对用户体验和学习率的影响研究 论坛讲者：章书飏, 车啸平, 曲晨鑫, 常恩耀

报告题目：基于LBS的位置隐私保护技术综述 论坛讲者：娄浩, 张磊, 李晶

报告题目：基于区块链的位置隐私保护研究 论坛讲者：贾园园, 李晶, 张磊

报告题目：基于混洗差分隐私的K-Modes聚类数据收集和发布方法 论坛讲者：蒋伟进, 陈艺琳, 韩裕清, 吴玉庭, 周为, 王海娟

报告题目：LBS中基于k-匿名的位置隐私保护综述 论坛讲者：刘苛

报告题目：基于事件的VR动作安全保护方法研究 论坛讲者：袁绍潭, 车啸平, 曲晨鑫, 常恩耀

报告题目：基于贝叶斯误差率的点击率可预测性量化方法研究 论坛讲者：习嘉琪, 於志文, 徐恩, 崔禾磊, 郭斌

报告题目：Multimodal Time Series Anomaly Detection Based on Graph Attention Networks 论坛讲者：芦新凯, 宋洪涛, 韩启龙

报告题目：Time Series Anomaly Detection Based on Adversarial Training and Wavelet Decomposition 论坛讲者：张钊, 宋洪涛, 韩启龙

报告题目：TransPPG: Two-stream Transformer for Remote Heart Rate Estimate 论坛讲者：康家琪, 杨夙, 张卫山

Session 3：城市计算与知识发现（2023年8月27日）

报告题目：面向轨道交通精准定位的超低功耗信标研究 论坛讲者：王周冀, 龚伟

报告题目：资源受限下基于因果推断的自动驾驶极端场景理解与识别 论坛讲者：冯饶, 唐蕾, 王瑞杰, 行本贝

报告题目：基于数字孪生的人流预测系统 论坛讲者：张诗怡, 陈超, 王程, 陈龙彪

报告题目：面向随机需求的基于预算分割的校车路径规划方法 论坛讲者：陈诗莹, 於志勇, 黄昉菀, 朱道也, 陈超

报告题目：基于预期收益的停车引导路线规划 论坛讲者：邱添立, 於志勇, 黄昉菀, 林滨伟,陈超

报告题目：基于多模态反馈的盲人驾驶系统设计与分析 论坛讲者：张睿哲, 赵莎, 杨蔚, 孙煜, 万华根, 姚林, 许威威, 李石坚, 潘纲

报告题目：基于强化学习的稀疏群智感知移动多智能体路径规划 论坛讲者：郝勇涛, 於志勇, 黄昉菀, 涂淳钰, 陈超

报告题目：基于运行时可伸缩算子融合的深度计算加速方法 论坛讲者：郭赛, 刘思聪, 方程, 郭斌, 於志文

报告题目：A Food Delivery Using Dynamic Routing and Packet Exchanging Method 论坛讲者：Sayekat Kumar Das, Surafel Kifetew Woldeyes

报告题目：Traffic Accident Risk Prediction Method of Urban Road Network Based on Multi-spatiotemporal Data 论坛讲者：姚祥忠, 张海涛

报告题目：MMa4CTR: 一个多模态信息增强的短视频推荐模型 论坛讲者：霍育福, 金蓓弘, 廖肇翊

报告题目：Few-shot Classification Based on Deep Bayes Network 论坛讲者：王金刚, 刘汝月, 印桂生, 张立国

报告题目：非平稳环境下的数据流分类算法 论坛讲者：詹舒, 李洋, 刘春颜, 赵蕴龙

报告题目：针对语言模型的平均随机梯度下降算法改进 论坛讲者：陈观林

报告题目：Target-Oriented Opinion Words Extraction as a Subtask of Aspect-Based Sentiment Classification: A Comprehensive Study on Utilizing Labelless Data in Natural Language Processing 论坛讲者：Sakaye Abdoulaye Hamadoun

报告题目：面向智能合约的漏洞检测方法 论坛讲者：张熠哲, 冯光升, 郑文祺, 李冰洋, 李伟

报告题目：一种融合预训练语言模型的知识增强命名实体识别方法 论坛讲者：王志远, 周强, 吴仍裕, 赵俊峰, 王亚沙

报告题目：面向人类知识的强化学习模型构建方法 论坛讲者：高伟

报告题目：GNN4MVR：一种基于图神经网络的短视频推荐模型 论坛讲者：廖肇翊, 金蓓弘, 霍育福

报告题目：Shredded Image Reassembly Method based on Graph Neural Network 论坛讲者：刘汝月, 汪溟浩, 王金刚, 印桂生, 张立国

报告题目：Approach to Enhance Accuracy of Semi-Asynchronous Federated Learning Model for Non-IID Data 论坛讲者：张云林, 金善玉, 玄世昌

报告题目：A Federated Multi-Task Learning Model Based on Task Priority in Ubiquitous Computing 论坛讲者：王嘉瑞, 张浩然, 玄世昌

报告题目：Underwater target detection based on dual inversion defogging and multi-scale feature fusion network 论坛讲者：魏连锁

报告题目：Multi-modal Fusion for Named Entity Recognition Based on De-biased Contrastive Learning 论坛讲者：李丽洁, 宋艳然, 王也, 刘文强, 徐凤鸣

Session 4：移动计算与物联网（2023年8月27日）

报告题目：基于贝叶斯博弈的编码边缘计算激励机制研究 论坛讲者：梁原博, 高平, 王亮, 於志文

报告题目：基于微服务架构的云机器人工作流优化调度机制 论坛讲者：郭浩浩, 王菁, 郭陈虹, 程留洋

报告题目：基于轻量化迁移学习的云边协同自然语言处理方法 论坛讲者：朱文强, 李洋, 刘春颜, 赵蕴龙

报告题目：跨移动边缘网络的联邦类增量学习方法 论坛讲者：李瑶, 郭斌, 刘琰, 张周阳子, 於志文

报告题目：基于BP神经网络的无线传感器网络非均匀分簇路由协议 论坛讲者：魏连锁

报告题目：面向多目标视频流分析的云边协同任务切分与调度机制研究 论坛讲者：曹书与, 彭清桦, 谢磊

报告题目：资源受限边端的分布式数据流优选与训练优化 论坛讲者：徐源, 刘思聪, 郭斌, 李晓晨, 於志文

报告题目：基于多任务互馈深度强化学习的无人机高效自适应决策方法 论坛讲者：高元, 刘思聪, 郭斌, 方程, 於志文

报告题目：IEAP:一种面向水声信号的特征表征方法 论坛讲者：王红滨, 梁露晴, 何鸣, 张帅, 杨芸玮

报告题目：基于多尺度注意力机制的水声特征提取方法 论坛讲者：何鸣, 孙均政, 王红滨, 沙忠澄

报告题目：基于UniXcoder的LLVM后端定制代码生成方法 论坛讲者：曹敏霞, 刘嘉琪, 吴艳霞

报告题目：3Deus：基于点云探测的复杂场景物品识别方法 论坛讲者：邱杰凡, 陈翰墨, 楼柯辰, 孙辰赫, 贾逸哲, 范菁

报告题目：针对可见光通信的声波窃听系统 论坛讲者：章一川, 季传英, 杨威, 林驰

报告题目：改进的CNN-LSTM无线传感器网络链路可靠性置信区间预测算法 论坛讲者：查明虎, 朱黎, 朱云云, 胡涛

报告题目：防无线蹭电系统的设计与实现 论坛讲者：杨威, 季传英, 章一川, 林驰

报告题目：存算一体深度学习模型终端优化部署方法 论坛讲者：罗诗妍, 郭斌, 刘思聪, 王梓琪, 於志文

报告题目：基于毫米波的转速测量系统 论坛讲者：季传英, 章一川, 杨威, 林驰

报告题目：基于事件驱动并发模型的LibOS 论坛讲者：张志辉, 胡先浪, 李伟, 吕宏武, 冯光升

报告题目：物联网中基于区块链和可信执行环境的访问控制方案 论坛讲者：蒋伟进, 李恩, 罗田甜, 周文颖, 杨莹

报告题目：增强现实机器人无线遥操作的视触同步方法 论坛讲者：陈雷, 许驰, 李琳, 封岸松

报告题目：基于热核扩散的类脑小世界储备池设计 论坛讲者：闫莹, 於志勇, 黄昉菀

报告题目：基于Lyapunov 引导的多智能体深度强化学习的动态任务卸载策略 论坛讲者：杨哲兴, 刘世康, 张永敏

报告题目：基于Transformer的OFDM通信系统的接收机设计 论坛讲者：岳丙蕾, 杨春, 张引

报告题目：基于BTMA的LoRa网络隐藏终端MAC协议研究 论坛讲者：陈国杰, 王璐, 何文锋, 伍楷舜

PCC 论坛：普适计算与人工智能的融合之路

论坛及人员简介
论坛简介：        普适计算和人工智能是当今科技发展的两大重要驱动力。普适计算的追求是将计算技术无处不在地融入我们的日常生活，而人工智能的目标则在于赋予机器智能和学习的能力。这两个领域的不断演进和融合，正在开创前所未有的科技前景，并对社会、经济和人类生活产生着深远的影响。本次论坛将聚焦于"普适计算与人工智能的融合之路"，深入研讨普适计算和人工智能领域的最新进展，以及它们如何在彼此的交汇点上形成更强大的创新动力。
论坛主席：谢   幸	讲者简介： 微软亚洲研究院资深首席研究员，中国科学技术大学兼职博士生导师，中国计算机学会普适计算专委会副主任。他的团队在数据挖掘、社会计算和负责任的人工智能等领域展开创新性的研究。他发表了400余篇学术论文，共被引用40000余次，H指数103，1999年获首届微软学者奖，2019年获ACM SIGSPATIAL十年影响力论文奖及中国计算机学会青竹奖，2020年获ACM SIGSPATIAL十年影响力论文荣誉奖，2021年获ACM SIGKDD China时间检验论文奖，2022年获ACM SIGKDD时间检验论文奖，2023年获IEEE MDM时间检验论文奖并入选DeepTech中国智能计算科技创新人物。他是中国计算机学会会士、IEEE会士、ACM杰出会员。
特邀讲者一：王亚沙	讲者简介： 北京大学长聘教授，教育部长江学者，软件工程国家工程研究中心副主任，全国信标委大数据标准工作组技术专题组组长。长期从事大数据分析、人工智能等领域的研究工作，在ICML、KDD、ICDE、AAAI、TKDE等国际人工智能、数据挖掘顶级学术期刊和会议发表论文百余篇，获得发明专利十余项。担任国家重点研发计划项目首席科学家，并承担国家多项自然科学基金、国家重大科技专项课题。研究成果获国家科技进步二等奖、国家教育部科技进步奖一等奖。
特邀讲者二：郭   斌	讲者简介： 工学博士，西北工业大学计算机学院教授、副院长，国家杰出青年科学基金获得者，人机物融合群智计算教育部重点实验室副主任，工信部智能感知与计算重点实验室副主任，西北工业大学计算与艺术交叉研究中心主任。入选教育部“新世纪优秀人才”（2012）和国家“万人计划”青年拔尖人才（2017），爱思唯尔中国高被引学者。主要从事智能物联与普适计算、群体智能、人机物融合群智计算等方面研究。在IEEE/ACM汇刊等国内外重要期刊和会议上发表论文150余篇，曾获得教育部自然科学一等奖、陕西省自然科学一等奖以及IEEE UIC’17、ISI’19、BIBM’20等国际会议“最佳论文奖”。担任《IEEE Transactions on Human-Machine Systems》、《IEEE Communications Magazine》、《ACM IMWUT》等国际权威期刊编委。IEEE高级会员，中国计算机学会CCF杰出会员、CCF西安分部主席。
特邀讲者三：房鼎益	讲者简介： 西北大学信息学院教授，现任陕西省无源物联网国际联合研究中心主任、西北大学物联网研究院院长。主要从事无源物联网、无线感知和软件安全保护等研究工作，在ACM/IEEE Mobicom、SIGCOMM、UbiComp和TON、TMC等发表论文200余篇。获陕西省科学技术二等奖和陕西高等学校科学技术一等奖等多项奖励。相关研究成果在陕西榆林明长城、甘肃锁阳城等遗产保护区和陕西柞水金米村木耳产业中示范应用，并曾被美国《每日科学》、英国 BBC和新华社等国内外媒体报道。
论坛讲者四：贾维嘉	讲者简介： 北师港浸大（UIC） 副校长（研究）、北京师范大学（珠海校区）人工智能与未来网络联合研究院主任。在加入北京师范大学/UIC之前，曾担任澳门大学智慧城市物联网国家重点实验室副主任和中国上海交通大学致远讲座教授，香港城市大学教授。研究方向为：智能边缘计算，最佳网络路由和部署；顶点覆盖；任播和组播协议；传感器网络；NLP与知识关系抽取。在国际期刊/会议以及研究书籍和书籍章节中发表了 600 多篇文章。曾获得2011/2012年深圳国际世博会最佳产品奖。获2017年教育部科研奖励一等奖（名列2）和多项省级科技奖励。曾担任各种知名国际期刊的区域编辑。在许多顶级国际会议任主席/ PC 成员/主讲人。他是IEEE会士和CCF杰出会员。
特邀讲者五：赵蕴龙	讲者简介： 教授、博导，物联网工程国家一流专业负责人，CCF普适计算专委常务委员，江苏省计算机学会系统结构专委副主任，入选江苏省“六大人才高峰”计划和南京领军型人才计划。主要研究方向为普适计算、群智计算、穿戴计算、无人系统安全和协同智能等，在航空航天、高端制造等行业开展了工业智能等研究工作，牵头一项ISO国际标准研制工作，承担国家重点研发计划、教育部新工科研究与实践项目等各类项目60多项，获得省部级等奖项5项。
特邀讲者六：金蓓弘	讲者简介： 中国科学院软件研究所研究员，博士生导师。中国计算机学会(CCF)杰出会员，任CCF普适计算专委会常委。长期从事分布式计算、普适计算领域的研发工作，当前的研究兴趣包括推荐系统、智能感知、物联网等。在AAAI、ACL、UbiComp、TMC、TKDE、TPDS等国际期刊、国际会议上发表论文150余篇，获得中国发明专利11项。曾获国家级科技进步奖励一次，省部级奖励三次。相关工作成果在爱奇艺、美团、MX Player等工业生产环境中得到部署和应用。

PCC 顶会顶刊论文交流论坛

Session 1：智能感知技术（2023年8月27日）

报告题目：Understanding the Mechanism of Through-Wall Wireless Sensing: A Model-based Perspective 论坛讲者：张化磊，王柱，孙卓，宋文超，任智慧，於志文，郭斌 出处：Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 报告摘要：During the last few years, there is a growing interest on the usage of Wi-Fi signals for human activity detection. A large number of Wi-Fi based sensing systems have been developed, including respiration detection, gesture classification, identity recognition, etc. However, the usability and robustness of such systems are still limited, due to the complexity of practical environments. Various pioneering approaches have been proposed to solve this problem, among which the model-based approach is attracting more and more attention, due to the advantage that it does not require a huge dataset for model training. Existing models are usually developed for Line-of-Sight (LoS) scenarios, and can not be applied to facilitating the design of wireless sensing systems in Non-Line-of-Sight (NLoS) scenarios (e.g., through-wall sensing). To fill this gap, we propose a through-wall wireless sensing model, aiming to characterize the propagation laws and sensing mechanisms of Wi-Fi signals in through-wall scenarios. Specifically, based on the insight that Wi-Fi signals will be refracted while there is a wall between the transceivers, we develop a refraction-aware Fresnel model, and prove theoretically that the original Fresnel model can be seen as a special case of the proposed model. We find that the presence of a wall will change the distribution of Fresnel zones, which we called the "squeeze effect" of Fresnel zones. Moreover, our theoretical analysis indicates that the "squeeze effect" can help improve the sensing capability (i.e., spatial resolution) of Wi-Fi signals. To validate the proposed model, we implement a through-wall respiration sensing system with a pair of transceivers. Extensive experiments in typical through-wall environments show that the respiration detection error is lower than 0.5 bpm, while the subject's vertical distance to the connection line of the transceivers is less than 200 cm. To the best of our knowledge, this is the first theoretical model that reveals the Wi-Fi based wireless sensing mechanism in through-wall scenarios.

报告题目：HearFire: Indoor Fire Detection via Inaudible Acoustic Sensing 论坛讲者：王征，王砚文，田蜜，沈家星 出处：Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 报告摘要：Indoor conflagration causes a large number of casualties and property losses worldwide every year. Yet existing indoor fire detection systems either suffer from short sensing range (e.g., ≤ 0.5m using a thermometer), susceptible to interferences (e.g., smoke detector) or high computational and deployment overhead (e.g., cameras, Wi-Fi). This paper proposes HearFire, a cost-effective, easy-to-use and timely room-scale fire detection system via acoustic sensing. HearFire consists of a collocated commodity speaker and microphone pair, which remotely senses fire by emitting inaudible sound waves. Unlike existing works that use signal reflection effect to fulfill acoustic sensing tasks, HearFire leverages sound absorption and sound speed variations to sense the fire due to unique physical properties of flame. Through a deep analysis of sound transmission, HearFire effectively achieves room-scale sensing by correlating the relationship between the transmission signal length and sensing distance. The transmission frame is carefully selected to expand sensing range and balance a series of practical factors that impact the system's performance. We further design a simple yet effective approach to remove the environmental interference caused by signal reflection by conducting a deep investigation into channel differences between sound reflection and sound absorption. Specifically, sound reflection results in a much more stable pattern in terms of signal energy than sound absorption, which can be exploited to differentiate the channel measurements caused by fire from other interferences. Extensive experiments demonstrate that HireFire enables a maximum 7m sensing range and achieves timely fire detection in indoor environments with up to 99.2% accuracy under different experiment configurations.

报告题目：Acoustic Sensing and Communication Using Metasurface 论坛讲者：Yongzhao Zhang, Yezhou Wang, Lanqing Yang, Mei Wang, Yi-Chao Chen, Lili Qiu, Yihong Liu, Guangtao Xue, Jiadi Yu 出处：20th USENIX Symposium on Networked Systems Design and Implementation, 2023 报告摘要：Acoustic sensing is increasingly popular owing to widely available devices that support them. Yet the sensing resolution and range are still limited due to limited bandwidth and sharp decay in the signal at inaudible frequencies. Inspired by recent development in acoustic metasurfaces, in this paper, we first perform an in-depth study of acoustic metasurface (AMS) and compare it with the phased array speaker. Our results show that AMS is attractive as it achieves a significant SNR increase while maintaining a compact size. A major limitation of existing AMS is its static configuration. Since our target may be at any possible location, it is important to support scanning in different directions. We develop a novel acoustic system that leverages a metasurface and a small number of speakers. We jointly optimize the configuration of metasurface and transmission signals from the speakers to achieve low-cost dynamic steering. Using a prototype implementation and extensive evaluation, we demonstrate its effectiveness in improving SNR, acoustic sensing accuracy, and acoustic communication reliability over a wide range of scenarios.

报告题目：Towards a Dynamic Inter-Sensor Correlations Learning Framework for Multi-Sensor-Based Wearable Human Activity Recognition 论坛讲者：缪盛欢，陈岭，胡容，罗映淞 出处：Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 报告摘要：Multi-sensor-based wearable human activity recognition (WHAR) is a research hotspot in the field of ubiquitous computing. Extracting effective features from multi-sensor data is essential to improve the performance of activity recognition. Despite the excellent achievements of previous works, the challenge remains for modelling the dynamic correlations between sensors. In this paper, we propose a lightweight yet efficient GCN-based dynamic inter-sensor correlations learning framework called DynamicWHAR for automatically learning the dynamic correlations between sensors. DynamicWHAR is mainly composed of two modules: Initial Feature Extraction and Dynamic Information Interaction. Firstly, Initial Feature Extraction module performs data-to-feature transformation to extract the initial features of each sensor. Subsequently, Dynamic Information Interaction module explicitly models the specific interaction intensity between any two sensors, and performs dynamic information aggregation between sensors by the learned interaction intensity. Extensive experiments on four diverse WHAR datasets and two different resource-constrained devices validate that DynamicWHAR outperforms the SOTA models in both recognition performance and computational complexity.

报告题目：WiMeasure: Millimeter-level Object Size Measurement with Commodity WiFi Devices 论坛讲者：Xuanzhi Wang，Niu Kai，Anlan Yu，Jie Xiong，Zhiyun Yao，Junzhe Wang，Wenwei Li，Daqing Zhang 出处：Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 报告摘要：In the past few years, a large range of wireless signals such as WiFi, RFID, UWB and Millimeter Wave were utilized for sensing purposes. Among these wireless sensing modalities, WiFi sensing attracts a lot of attention owing to the pervasiveness of WiFi infrastructure in our surrounding environments. While WiFi sensing has achieved a great success in capturing the target's motion information ranging from coarse-grained activities and gestures to fine-grained vital signs, it still has difficulties in precisely obtaining the target size owing to the low frequency and small bandwidth of WiFi signals. Even Millimeter Wave radar can only achieve a very coarse-grained size measurement. High precision object size sensing requires using RF signals in the extremely high-frequency band (e.g., Terahertz band). In this paper, we utilize low-frequency WiFi signals to achieve accurate object size measurement without requiring any learning or training. The key insight is that when an object moves between a pair of WiFi transceivers, the WiFi CSI variations contain singular points (i.e., singularities) and we observe an exciting opportunity of employing the number of singularities to measure the object size. In this work, we model the relationship between the object size and the number of singularities when an object moves near the LoS path, which lays the theoretical foundation for the proposed system to work. By addressing multiple challenges, for the first time, we make WiFi-based object size measurement work on commodity WiFi cards and achieve a surprisingly low median error of 2.6 mm. We believe this work is an important missing piece of WiFi sensing and opens the door to size measurement using low-cost low-frequency RF signals.

报告题目：LT-Fall: The Design and Implementation of a Life-threatening Fall Detection and Alarming System 论坛讲者：张舵，张旭升，李晟洁，谢亚雄，李洋，王炫之，张大庆 出处：Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 报告摘要：Falls are the leading cause of fatal injuries to elders in modern society, which has motivated researchers to propose various fall detection technologies. We observe that most of the existing fall detection solutions are diverging from the purpose of fall detection: timely alarming the family members, medical staff or first responders to save the life of the human with severe injury caused by fall. Instead, they focus on detecting the behavior of human falls, which does not necessarily mean a human is in real danger. The real critical situation is when a human cannot get up without assistance and is thus lying on the ground after the fall because of losing consciousness or becoming incapacitated due to severe injury. In this paper, we define a life-threatening fall as a behavior that involves a falling down followed by a long-lie of humans on the ground, and for the first time point out that a fall detection system should focus on detecting life-threatening falls instead of detecting any random falls. Accordingly, we design and implement LT-Fall, a mmWave-based life-threatening fall detection and alarming system. LT-Fall detects and reports both fall and fall-like behaviors in the first stage and then identifies life-threatening falls by continuously monitoring the human status after fall in the second stage. We propose a joint spatio-temporal localization technique to detect and locate the micro-motions of the human, which solves the challenge of mmWave's insufficient spatial resolution when the human is static, i.e., lying on the ground. Extensive evaluation on 15 volunteers demonstrates that compared to the state-of-the-art work (92% precision and 94% recall), LT-Fall achieves zero false alarms as well as a precision of 100% and a recall of 98.8%.

报告题目：CamRadar: Hidden Camera Detection Leveraging Amplitude-modulated Sensor Images Embedded in Electromagnetic Emanations 论坛讲者：Ziwei Liu，Feng Lin，Chao Wang，Yijie Shen，Zhongjie Ba，Li Lu，Wenyao Xu 出处：Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 报告摘要：Hidden cameras in sensitive locations have become an increasing threat to personal privacy all over the world. Because the camera is small and camouflaged, it is difficult to detect the presence of the camera with naked eyes. Existing works on this subject have either only covered using wireless transmission to detect cameras, or using other methods which are cumbersome in practical use. In this paper, we introduce a new direction that leverages the unintentional electromagnetic (EM) emanations of the camera to detect it. We first find that the digital output of the camera's image sensor will be amplitude-modulated to the EM emanations of the camera's clock. Thus, changes in the scope of the camera will directly cause changes in the camera's EM emanations, which constitutes a unique characteristic for a hidden camera. Based on this, we propose a novel camera detection system named CamRadar, which can filter out potential camera EM emanations from numerous EM signals quickly and achieve accurate hidden camera detection. Benefitting from the camera's EM emanations, CamRadar will not be limited by the camera transmission types or the detection angle. Our extensive real-world experiments using CamRadar and 19 hidden cameras show that CamRadar achieves a fast detection (in 16.75s) with a detection rate of 93.23% as well as a low false positive rate of 3.95%.

报告题目：CHAR: Composite Head-body Activities Recognition with A Single Earable Device 论坛讲者：朱培钊，邹永攀，黎文源，伍楷舜 出处：2023 IEEE International Conference on Pervasive Computing and Communications (PerCom) 报告摘要：The increasing popularity of earable devices stimulates great academic interest to design novel head gesture-based interaction technologies. But existing works simply consider it as a singular activity recognition problem. This is not in line with practice since users may have different body movements such as walking and jogging along with head gestures. It is also beneficial to recognize body movements during human-device interaction since it provides useful context information. As a result, it is significant to recognize such composite activities in which actions of different body parts happen simultaneously. In this paper, we propose a system called CHAR to recognize composite head-body activities with a single IMU sensor. The key idea of our solution is to make use of the inter-correlation of different activities and design a multi-task learning network to extract shared and specific representations. We implement a real-time prototype and conduct extensive experiments to evaluate it. The results show that CHAR can recognize 60 kinds of composite activities (12 head gestures and 5 body movements) with high accuracies of 97.0% and 89.7% in user- dependent and independent cases, respectively.

报告题目：Human Parsing with Joint Learning for Dynamic mmWave Radar Point Cloud 论坛讲者：Shuai Wang，Dongjiang Cao，Ruofeng Liu，Wenchao Jiang，Tianshun Yao，Chris Xiaoxuan Lu 出处：Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 报告摘要：Human sensing and understanding is a key requirement for many intelligent systems, such as smart monitoring, human-computer interaction, and activity analysis, etc. In this paper, we present mmParse, the first human parsing design for dynamic point cloud from commercial millimeter-wave radar devices. mmParse proposes an end-to-end neural network design that addresses the inherent challenges in parsing mmWave point cloud (e.g., sparsity and specular reflection). First, we design a novel multi-task learning approach, in which an auxiliary task can guide the network to understand human structural features. Secondly, we introduce a multi-task feature fusion method that incorporates both intra-task and inter-task attention to aggregate spatio-temporal features of the subject from a global view. Through extensive experiments in both indoor and outdoor environments, we demonstrate that our proposed system is able to achieve ~ 92% accuracy and ~ 84% IoU accuracy. We also show that the predicted semantic labels can increase the performance of two downstream tasks (pose estimation and action recognition) by ~ 18% and ~ 6% respectively.

报告题目：Cross Vision-RF Gait Re-identification with Low-cost RGB-D Cameras and mmWave Radars 论坛讲者：DONGJIANG CAO，RUOFENG LIU，HAO LI，SHUAI WANG，WENCHAO JIANG，CHRIS XIAOXUAN LU 出处：Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 报告摘要：Human identification is a key requirement for many applications in everyday life, such as personalized services, automatic surveillance, continuous authentication, and contact tracing during pandemics, etc. This work studies the problem of cross-modal human re-identification (ReID), in response to the regular human movements across camera-allowed regions (e.g., streets) and camera-restricted regions (e.g., offices) deployed with heterogeneous sensors. By leveraging the emerging low-cost RGB-D cameras and mmWave radars, we propose the first-of-its-kind vision-RF system for cross-modal multi-person ReID at the same time. Firstly, to address the fundamental inter-modality discrepancy, we propose a novel signature synthesis algorithm based on the observed specular reflection model of a human body. Secondly, an effective cross-modal deep metric learning model is introduced to deal with interference caused by unsynchronized data across radars and cameras. Through extensive experiments in both indoor and outdoor environments, we demonstrate that our proposed system is able to achieve ~ 92.5% top-1 accuracy and ~ 97.5% top-5 accuracy out of 56 volunteers. We also show that our proposed system is able to robustly reidentify subjects even when multiple subjects are present in the sensors' field of view.

报告题目：Embracing Consumer-level UWB-equipped Devices for Fine-grained Wireless Sensing 论坛讲者：张扶桑，常兆心，熊杰，马俊麒，倪嘉志，张文博，金蓓弘，张大庆 出处：Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 报告摘要：RF sensing has been actively exploited in the past few years to enable novel IoT applications. Among different wireless technologies, WiFi-based sensing is most popular owing to the pervasiveness of WiFi infrastructure. However, one critical issue associated with WiFi sensing is that the information required for sensing can not be obtained from consumer-level devices such as smartphones or smart watches. The commonly-seen WiFi devices in our everyday lives actually can not be utilized for sensing. Instead, dedicated hardware with a specific WiFi card (e.g., Intel 5300) needs to be used for WiFi sensing. This paper involves Ultra-Wideband (UWB) into the ecosystem of RF sensing and makes RF sensing work on consumer-level hardware such as smartphones and smart watches for the first time. We propose a series of methods to realize UWB sensing on consumer-level electronics without any hardware modification. By leveraging fine-grained human respiration monitoring as the application example, we demonstrate that the achieved performance on consumer-level electronics is comparable to that achieved using dedicated UWB hardware. We show that UWB sensing hosted on consumer-level electronics is able to achieve fine granularity, robustness against interference and also multi-target sensing, pushing RF sensing one step towards real-life adoption.

报告题目：ECG-grained Cardiac Monitoring Using UWB Signals 论坛讲者：王志，金蓓弘，李思恒，张扶桑，张文博 出处：Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 报告摘要：With the development of wireless sensing, researchers have proposed many contactless vital sign monitoring systems, which can be used to monitor respiration rates, heart rates, cardiac cycles and etc. However, these vital signs are ones of coarse granularity, so they are less helpful in the diagnosis of cardiovascular diseases (CVDs). Considering that electrocardiogram (ECG) is an important evidence base for the diagnoses of CVDs, we propose to generate ECGs from ultra-wideband (UWB) signals in a contactless manner as a fine-grained cardiac monitoring solution. Specifically, we analyze the properties of UWB signals containing heartbeats and respiration, and design two complementary heartbeat signal restoration methods to perfectly recover heartbeat signal variation. To establish the mapping between the mechanical activity of the heart sensed by UWB devices and the electrical activity of the heart recorded in ECGs, we construct a conditional generative adversarial network to encode the mapping between mechanical activity and electrical activity and propose a contrastive learning strategy to reduce the interference from noise in UWB signals. We build the corresponding cardiac monitoring system named RF-ECG and conduct extensive experiments using about 120,000 heartbeats from more than 40 participants. The experimental results show that the ECGs generated by RF-ECG have good performance in both ECG intervals and morphology compared with the ground truth. Moreover, diseases such as tachycardia/bradycardia, sinus arrhythmia, and premature contractions can be diagnosed from the ECGs generated by our RF-ECG.

报告题目：Industrial Vision: Rectifying Millimeter-Level Edge Deviation in Industrial Internet of Things with Camera-based Edge Device 论坛讲者：Lei Xie，Zihao Chu，Yi Li，Tao Gu，Yanling Bu，Chuyu Wang，Sanglu Lu 出处：IEEE Transactions on Mobile Computing ( Early Access ) 报告摘要：Nowadays, to realize the intelligent manufacturing in Industrial Internet of Things (IIoT) scenarios, novel approaches in computer vision are in great demand to tackle the new challenges in IIoT environment. These approaches, which we call Industrial Vision , are expected to offer customized solutions for intelligent manufacturing in an accurate, time efficient and robust manner. In this paper, we propose a novel approach to industrial vision, called Edge-Eye , to rectify the edge deviation automatically for Irradiated Cross-linked Polyethylene Foam (IXPE) production with millimeter-level accuracy. IXPE has been one of the most commonly used materials in industry. During the production process of IXPE sheets, their edges need keep aligned strictly, otherwise, they could quickly get out of the border of the rolling plate and cause the huge economic loss. We deploy a commercial camera with mobile edge node in front of the IXPE sheet to continuously detect and rectify the edge deviation. Particularly, to handle the complex production environment when extracting the edge of IXPE sheet, we deploy a pair of reference bars with high-contrast colors to efficiently differentiate the sheet edge from the background. Then, we propose a Bi-direction Edge Tracking method to perform the edge detection from both vertical and horizontal aspects. To realize the rectification using mobile edge nodes with limited computing resources, we reduce the cost of computation by extracting the Minimized Region of Interest , i.e., the edge area overlapped with the higher contrast reference bar on both sides. We further design a negative feedback control system with multi-stage feedback regulation mechanism, keeping the edge deviation within millimeter-level . We implemented Edge-Eye on the ARM64 platform and performed evaluation in the practical IXPE production process. The experimental results show that Edge-Eye achieves the average accuracy of 5 mm for the edge deviation rectification, with the average latency of 200 ms for edge deviation detection. During the process of 20-month real deployment for 36 production lines, 66 manpower per day (90% of the overall manpower) has been saved, and the utilization rate of IXPE material increases from 87% to 94%.

报告题目：MultiResp: Robust Respiration Monitoring for Multiple Users using Acoustic Signal 论坛讲者：王天本，李张本，刘现涛，顾涛，严宏昊，吕静，胡瑾，张大庆 出处：IEEE Transactions on Mobile Computing ( Early Access ) 报告摘要：In recent years, we have seen efforts made to monitor respiration for multiple users. Existing approaches capture chest movement relying on signals directly reflected from chest or separate breath waves based on breath rate difference between subjects. However, several limitations exist: 1) they may fail when subjects face away from the transceiver or are blocked by obstacles or other subjects; 2) they may fail to separate subjects' breath waves with the same or similar rates (i.e., breath rate difference < 1 bpm); 3) they assume a priori knowledge of number of subjects and cannot adapt to dynamic change of subject number during monitoring. To overcome these limitations, in this paper we propose MultiResp , a multi-user respiration monitoring system using acoustic signal. By fully leveraging the abundant acoustic signals reflected indirectly from subjects' chest, MultiResp can robustly capture chest movement even when they face away from the transceiver or are blocked. By extracting fine-grained breath rate and phase difference between different subjects, MultiResp can separate the breath waves with the same or similar rates and adapt to dynamic change of subject number during monitoring. Extensive experiments show that MultiResp is able to accurately monitor the respiration of multiple users with a median error of 0.3 bpm in various indoor scenarios, however, it fails when the sound pressure is lower than 55 dB or body movement is happening.

报告题目：WISE: Low-Cost Wide Band Spectrum Sensing Using UWB 论坛讲者：罗志成，黄倩怡，王锐，陈昊，陶小峰，陈贵海，张黔 出处：Proceedings of the 20th ACM Conference on Embedded Networked Sensor Systems 报告摘要：Spectrum sensing plays a crucial role in spectrum monitoring and management. However, due to the expensive cost of high-speed ADCs, wideband spectrum sensing is a long-standing challenge. In this paper, we present how to transform Ultra-wideband (UWB) devices into a spectrum sensor which can provide wideband spectrum monitoring at a low cost. Compared with the expensive high-speed ADCs which cost at least hundreds of dollars, a UWB device is only several dollars. As the low-cost UWB technology is not originally designed for spectrum sensing, we address the inherent limitations of low-cost devices such as limited memory, low SPI speed and low accuracy, and show how to obtain spectrum occupancy information from the noisy and spurious UWB channel impulse response. In this paper, we present WISE, which not only can give accurate channel occupancy information, but also can precisely estimate the signal power and bandwidth. WISE can also detect fleeting radar signals. We implement WISE and perform extensive evaluations with both controlled experiments and field tests. Results show that WISE can sense up to 900MHz bandwidth and the power estimation error is less than 3dB. WISE can also accurately detect busy 5G channels. We believe that WISE provides a new paradigm for low-cost wideband spectrum sensing, which is critical for large-scale fine-grained spectrum monitoring.

报告题目：Loan Fraud Users Detection in Online Lending Leveraging Multiple Data Views 论坛讲者：Sha Zhao，Yongrui Huang，Ling Chen，Chunping Wang，Shijian Li，Lei Chen，Gang Pan 出处：Association for the Advancement of Artificial Intelligence 2023 报告摘要：In recent years, online lending platforms have been becoming attractive for micro-financing and popular in financial industries. However, such online lending platforms face a high risk of failure due to the lack of expertise on borrowers' creditworthness. Thus, risk forecasting is important to avoid economic loss. Detecting loan fraud users in advance is at the heart of risk forecasting. The purpose of fraud user (borrower) detection is to predict whether one user will fail to make required payments in the future. Detecting fraud users depend on historical loan records. However, a large proportion of users lack such information, especially for new users. In this paper, we attempt to detect loan fraud users from cross domain heterogeneous data views, including user attributes, installed app lists, app installation behaviors, and app-in logs, which compensate for the lack of historical loan records. However, it is difficult to effectively fuse the multiple heterogeneous data views. Moreover, some samples miss one or even more data views, increasing the difficulty in fusion. To address the challenges, we propose a novel end-to-end deep multiview learning approach, which encodes heterogeneous data views into homogeneous ones, generates the missing views based on the learned relationship among all the views, and then fuses all the views together to a comprehensive view for identifying fraud users. Our model is evaluated on a real-world large-scale dataset consisting of 401,978 loan records of 228,117 users from January 1, 2019, to September 30, 2019, achieving the state-of-the-art performance.

报告题目：Player Behavior Modeling for Enhancing Role-Playing Game Engagement 论坛讲者：Sha Zhao，Yizhi Xu，Zhiling Luo，Jianrong Tao，Shijian Li，Changjie Fan，Gang Pan 出处：IEEE Transactions on Computational Social Systems 报告摘要：Role-playing games (RPGs) are one of the most exciting and most rapidly expanding genres of online games. Virtual characters that are not controlled by players, have become an integral part, which helps to advance narratives of RPGs. Believable characters can enhance game engagement and further improve player retention. However, game players easily find that most characters' behaviors are limited and improbable, resulting in a less meaningful game experience. In this work, we propose a framework to model game behaviors to learn behavior patterns of human players. Based on the learned behavior patterns, it generates human-like action sequences that can be used for the design of believable virtual characters in RPGs, so as to enhance game engagement. Specifically, considering the influence of game context in behavior patterns, we integrate game context (players' levels and game classes) with actions together to model behaviors. We propose a long-term memory cell on actions and game context to learn the hidden representations. We also introduce an attention mechanism to measure the contribution of the actions previously performed to the next action. Given only one action, our model can generate action sequences by predicting the succeeding action based on the previously generated actions. The model was evaluated on a real-world data set of over 22 000 players and more than 51 million action logs of an RPG game in 21 days. The results demonstrate the state-of-the-art performance.

报告题目：Multi-Vib: Precise Multi-point Vibration Monitoring Using mmWave Radar 论坛讲者：Yanni Yang，Jiannong Cao 出处：Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 报告摘要：Vibration measurement is vital for fault diagnosis of structures (e.g., machines and civil structures). Different structure components undergo distinct vibration patterns, which jointly determine the structure's health condition, thus demanding simultaneous multi-point vibration monitoring. Existing solutions deploy multiple accelerometers along with their power supplies or laser vibrometers on the monitored object to measure multi-point vibration, which is inconvenient and costly. Cameras provide a less expensive solution while heavily relying on good lighting conditions. To overcome these limitations, we propose a cost-effective and passive system, called Multi-Vib, for precise multi-point vibration monitoring. Multi-Vib is implemented using a single mmWave radar to remotely and separately sense the vibration displacement of multiple points via signal reflection. However, simultaneously detecting and monitoring multiple points on a single object is a daunting task. This is because most radar signals are scattered away from vibration points due to their tilted locations and shapes by nature, causing an extremely weak reflected signal to the radar. To solve this issue, we dedicatedly design a physical marker placed on the target point, which can force the direction of the reflected signal towards the radar and significantly increase the reflected signal strength. Another practical issue is that the reflected signal from each point endures interferences and noises from the surroundings. Thus, we develop a series of effective signal processing methods to denoise the signal for accurate vibration frequency and displacement estimation. Extensive experimental results show that the average errors in multi-point vibration frequency and displacement estimation are around 0.16Hz and 14μm, respectively.

报告题目：ASR: Efficient and Adaptive Stochastic Resonance for Weak Signal Detection 论坛讲者：Xingyu Chen，Jia Liu，Xu Zhang，Lijun Chen 出处：Proc. of IEEE INFOCOM, 2023 报告摘要：Weak-signal detection underlies a variety of ubiquitous computing applications, such as wireless sensing and machinery fault diagnosis. Stochastic resonance (SR) provides a new way for weak-signal detection by boosting undetectable signals with added white noise. However, existing work has to take a long time to search optimal parameter settings for SR, which cannot fit well some time-critical applications. In this paper, we propose an adaptive SR scheme (ASR) that can amplify the original signal at a low cost in time. The basic idea is that we find that the potential parameter is a key factor that determines the performance of SR. By treating the system as a feedback loop, we can dynamically adjust the potential parameters according to the output signals and make SR happen adaptively. ASR answered two technical questions: how can we evaluate the output signal and how can we tune the potential parameters quickly towards the optimal. In ASR, we first design a spectral-analysis based solution to examine whether SR happens using continuous wavelet transform. After that, we reduce the parameter tuning problem to a constrained non-linear optimization problem and use the sequential quadratic programming to iteratively optimize the potential parameters. We implement ASR and apply it in two ubiquitous computing applications: respiration-rate detection and machinery fault diagnosis. Extensive experiments show that ASR outperforms the state-of-the-art.

报告题目：Automatic Update for Wi-Fi Fingerprinting Indoor Localization via Multi-Target Domain Adaptation 论坛讲者：Jiankun Wang, Zenghua Zhao, Mengling Ou, Jiayang Cui, Bin Wu 出处：Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 报告摘要：Wi-Fi fingerprinting system in the long term suffers from gradually deteriorative localization accuracy, leading to poor user experiences. To keep high accuracy yet at a low cost, we first study long-term variation of access points (APs) and characteristics of their Wi-Fi signals through over-one-year experiments. Motivated by the experimental findings, we then design MTLoc, a Multi-Target domain adaptation network-based Wi-Fi fingerprinting Localization system. As the core, MTDAN (Multi-Target Domain Adaptation Network) model adopts the framework of generative adversarial network to learn time-invariant, time-specific, and location-aware features from the source and target domains. To enhance the alignment among the source and targets, two-level cycle consistency constraints are proposed. Hence, MTDAN is able to transfer location knowledge from the source domain to multiple targets. In addition, domain selection and outlier detection are designed to avoid explosive growth of storage for targets and to limit the impact of random variations of Wi-Fi signals. Extensive experiments are carried out on five datasets collected over two years in various real-world indoor environments with a total area of 8, 350 m2. Experimental results demonstrate that MTLoc retains high localization accuracy with limited storage and training cost in the long term, which significantly outperforms its counterparts. We share our dataset to the community for other researchers to validate our results and conduct further research.

报告题目：SWL-Adapt: An Unsupervised Domain Adaptation Model with Sample Weight Learning for Cross-User Wearable Human Activity Recognition 论坛讲者：胡容，陈岭，缪盛欢，汤星 出处：Association for the Advancement of Artificial Intelligence 2023 报告摘要：In practice, Wearable Human Activity Recognition (WHAR) models usually face performance degradation on the new user due to user variance. Unsupervised domain adaptation (UDA) becomes the natural solution to cross-user WHAR under annotation scarcity. Existing UDA models usually align samples across domains without differentiation, which ignores the difference among samples. In this paper, we propose an unsupervised domain adaptation model with sample weight learning (SWL-Adapt) for cross-user WHAR. SWL-Adapt calculates sample weights according to the classification loss and domain discrimination loss of each sample with a parameterized network. We introduce the meta-optimization based update rule to learn this network end-to-end, which is guided by meta-classification loss on the selected pseudo-labeled target samples. Therefore, this network can fit a weighting function according to the cross-user WHAR task at hand, which is superior to existing sample differentiation rules fixed for special scenarios. Extensive experiments on three public WHAR datasets demonstrate that SWL-Adapt achieves the state-of-the-art performance on the cross-user WHAR task, outperforming the best baseline by an average of 3.1% and 5.3% in accuracy and macro F1 score, respectively.

报告题目：Tensor-based Confident Information Coverage Reliability of Hybrid Internet of Things 论坛讲者：范晓萱, 邓贤君, 夏云芝, 易灵芝, Laurence T. Yang, 朱晨露 出处：IEEE Transactions on Mobile Computing ( Early Access ) 报告摘要：The widespread applications of the Hybrid Internet of Things (HIoT) have put forward higher requirements for network reliability. Coverage reliability is one of the important metrics of reliability, and reliable coverage ensures network data perception and transmission to improve the Quality of Service (QoS). In this paper, we define Confident Information Coverage Reliability ( CICR ) based on the Confident Information Coverage Model (CIC), which comprehensively considers sensor multistate, sensor energy, coverage rate, and connectivity robustness to evaluate coverage reliability. Furthermore, a Tensor-based Confident Information Coverage Reliability Algorithm (T-CICR) is proposed based on tensor modeling to evaluate CICR . The algorithm uses a tensor-based Markov model to predict sensor multistate. Three tensors of coverage rate, sensor multistate, and sensor energy are constructed to provide unified representations. Simulation results show that our proposed algorithm can significantly improve coverage reliability in terms of duty cycle, coverage rate requirement, sensing range, Root Mean Square Error (RMSE) threshold, connectivity robustness requirement, and link reliability.

Session 2：物联网大数据与人工智能（2023年8月27日）

报告题目：VoiceCloak: Adversarial Example Enabled Voice De-Identification with Balanced Privacy and Utility 论坛讲者：陈锰，卢立，王俊皓，俞嘉地，Yingying Chen，王志波，巴钟杰，林峰，任奎 出处：Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 报告摘要：Faced with the threat of identity leakage during voice data publishing, users are engaged in a privacy-utility dilemma when enjoying the utility of voice services. Existing machine-centric studies employ direct modification or text-based re-synthesis to de-identify users' voices but cause inconsistent audibility for human participants in emerging online communication scenarios, such as virtual meetings. In this paper, we propose a human-centric voice de-identification system, VoiceCloak, which uses adversarial examples to balance the privacy and utility of voice services. Instead of typical additive examples inducing perceivable distortions, we design a novel convolutional adversarial example that modulates perturbations into real-world room impulse responses. Benefiting from this, VoiceCloak could preserve user identity from exposure by Automatic Speaker Identification (ASI), while remaining the voice perceptual quality for non-intrusive de-identification. Moreover, VoiceCloak learns a compact speaker distribution through a conditional variational auto-encoder to synthesize diverse targets on demand. Guided by these pseudo targets, VoiceCloak constructs adversarial examples in an input-specific manner, enabling any-to-any identity transformation for robust de-identification. Experimental results show that VoiceCloak could achieve over 92% and 84% successful de-identification on mainstream ASIs and commercial systems with excellent voiceprint consistency, speech integrity, and audio quality.

报告题目：INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging 论坛讲者：范晓亮，陈龙彪 出处：Proceedings of the ACM Web Conference 2023 报告摘要：Spatio-temporal kriging is an important problem in web and social applications, such as Web or Internet of Things, where things (e.g., sensors) connected into a web often come with spatial and temporal properties. It aims to infer knowledge for (the things at) unobserved locations using the data from (the things at) observed locations during a given time period of interest. This problem essentially requires inductive learning. Once trained, the model should be able to perform kriging for different locations including newly given ones, without retraining. However, it is challenging to perform accurate kriging results because of the heterogeneous spatial relations and diverse temporal patterns. In this paper, we propose a novel inductive graph representation learning model for spatio-temporal kriging. We first encode heterogeneous spatial relations between the unobserved and observed locations by their spatial proximity, functional similarity, and transition probability. Based on each relation, we accurately aggregate the information of most correlated observed locations to produce inductive representations for the unobserved locations, by jointly modeling their similarities and differences. Then, we design relation-aware gated recurrent unit (GRU) networks to adaptively capture the temporal correlations in the generated sequence representations for each relation. Finally, we propose a multi-relation attention mechanism to dynamically fuse the complex spatio-temporal information at different time steps from multiple relations to compute the kriging output. Experimental results on three real-world datasets show that our proposed model outperforms state-of-the-art methods consistently, and the advantage is more significant when there are fewer observed locations. Our code is available at https://github.com/zhengchuanpan/INCREASE.

报告题目：DeepGPS: Deep Learning Enhanced GPS Positioning in Urban Canyons 论坛讲者：刘志丹，刘键聪，徐小雯，伍楷舜 出处：IEEE Transactions on Mobile Computing, 2022 报告摘要：Global Positioning System (GPS) has benefited many novel applications, e.g. , navigation, ride-sharing, and location-based services, in our daily life. Although GPS works well in most places, its performance in urban canyons is well-known poor, due to the signal reflections of non-line-of-sight (NLOS) satellites. Tremendous efforts have been made to mitigate the impacts of NLOS signals, while previous works heavily rely on precise proprietary 3D city models or other third-party resources, which are not easily accessible. In this paper, we present DeepGPS , a deep learning enhanced GPS positioning system that can correct GPS estimations by only considering some simple contextual information. DeepGPS fuses environmental factors, including building heights and road distribution around GPS's initial position, and satellite statuses to describe the positioning context, and exploits an encoder-decoder network model to implicitly learn the complex relationships between positioning contexts and GPS estimations from massive labeled GPS samples. As a result, the well-trained model can accurately predict the correct position for each erroneous GPS estimation given its positioning context. We further improve the model with a novel constraint mask to filter out invalid candidate locations, and enable continuous localization with a simple mobility model. A prototype system is implemented and experimentally evaluated using a large-scale bus trajectory dataset and real-field GPS measurements. Experimental results demonstrate that DeepGPS significantly enhances GPS performance in urban canyons, e.g. , on average effectively correcting 90.1% GPS estimations with accuracy improvement by 64.6%.

报告题目：Multi-UAV Trajectory Optimization for Servicing Dynamic Demands and Charging Battery 论坛讲者：张潇 出处：IEEE TRANSACTIONS ON MOBILE COMPUTING 报告摘要：Unmanned Aerial Vehicle (UAV) technology is a promising solution for providing high-quality mobile services (e.g., edge computing, fast Internet connection, and local caching) to ground users, where a UAV with limited service coverage travels among multiple geographical user locations (e.g., hotspots) for servicing their demands locally. How to dynamically determine a UAV swarm's cooperative path planning to best meet many users' spatio-temporally distributed demands is an important question but is unaddressed in the literature. To our best knowledge, this paper is the first to design and analyze cooperative path planning algorithms of a large UAV swarm for optimally servicing many spatial locations, where ground users' demands are released dynamically in the long time horizon. Regarding a single UAV's path planning design, we manage to substantially simplify the traditional dynamic program and propose an optimal algorithm of low computation complexity, which is only polynomial with respect to both the numbers of spatial locations and user demands. After coordinating a large number $K$ of UAVs, this simplified dynamic optimization problem becomes intractable and we alternatively present a fast iterative cooperation algorithm with provable approximation ratio $1-(1-\frac{1}{K})^{K}$ in the worst case, which is proved to obviously outperform the traditional approach of partitioning UAVs to serve different location clusters separately. To relax UAVs' battery capacity limit for sustainable service provisioning, we further allow UAVs to travel to charging stations in the mean time and thus jointly design UAVs' path planning over users' locations and charging stations. Despite of the problem difficulty, for the optimal solution, we successfully transform the problem to an integer linear program by creating novel directed acyclic graph of the UAV-state transition diagram, and propose an iterative algorithm with constant approximation ratio. Finally, we validate the theoretical results by extensive simulations.

报告题目：Altruistic and Profit-oriented: Making Sense of Roles in Web3 Community from Airdrop Perspective 论坛讲者：樊四正，闵天，吴啸，蔡玮 出处：Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems 报告摘要：Regardless of which community, incentivizing users is a necessity for well-sustainable operations. In the blockchain-backed Web3 communities, known for their transparency and security, airdrop serves as a widespread incentive mechanism for allocating capital and power. However, it remains a controversy on how to justify airdrop to incentive and empower the decentralized governance. In this paper, we use ParaSwap as an example to propose a role taxonomy methodology through a data-driven study to understand the characteristic of community members and the effectiveness of airdrop. We find that users receive more rewards tend to take positive actions towards the community. We summarize several arbitrage patterns and confirm the current detection is not sufficient in screening out airdrop hunters. In conjunction with the results, we discuss from the aspects of interaction, financialization, and system design to conclude the challenges and possible research directions for decentralized communities.

报告题目：Side-lobe Can Know More: Towards Simultaneous Communication and Sensing for mmWave 论坛讲者：Qian Yang，Hengxin Wu，Qianyi Huang，Jin Zhang，Hao Chen，Weichao Li，Xiaofeng Tao，Qian Zhang 出处：Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 报告摘要：Thanks to the wide bandwidth, large antenna array, and short wavelength, millimeter wave (mmWave) has superior performance in both communication and sensing. Thus, the integration of sensing and communication is a developing trend for the mmWave band. However, the directional transmission characteristics of the mmWave limits the sensing scope to a narrow sector. Existing works coordinate sensing and communication in a time-division manner, which takes advantage of the sector level sweep during the beam training interval for sensing and the data transmission interval for communication. Beam training is a low frequency (e.g., 10Hz) and low duty-cycle event, which makes it hard to track fast movement or perform continuous sensing. Such time-division designs imply that we need to strike a balance between sensing and communication, and it is hard to get the best of both worlds. In this paper, we try to solve this dilemma by exploiting side lobes for sensing. We design Sidense, where the main lobe of the transmitter is directed towards the receiver, while in the meantime, the side lobes can sense the ongoing activities in the surrounding. In this way, sensing and downlink communication work simultaneously and will not compete for hardware and radio resources. In order to compensate for the low antenna gain of side lobes, Sidense performs integration to boost the quality of sensing signals. Due to the uneven side-lobe energy, Sidense also designs a target separation scheme to tackle the mutual interference in multi-target scenarios. We implement Sidense with Sivers mmWave module. Results show that Sidense can achieve millimeter motion tracking accuracy at 6m. We also demonstrate a multi-person respiration monitoring application. As Sidense does not modify the communication procedure or the beamforming strategy, the downlink communication performance will not be sacrificed due to concurrent sensing. We believe that more fascinating applications can be implemented on this concurrent sensing and communication platform.

报告题目：Multimodal Fusion Framework Based on Statistical Attention and Contrastive Attention for Sign Language Recognition 论坛讲者：张江涛，王青山，王琦，郑志文 出处：IEEE Transactions on Mobile Computing ( Early Access ) 报告摘要：Sign language recognition (SLR) enables hearing-impaired people to better communicate with able-bodied individuals. The diversity of multiple modalities can be utilized to improve SLR. However, existing multimodal fusion methods do not take into account multimodal interrelationships in-depth. This paper proposes SeeSign: a multimodal fusion framework based on statistical attention and contrastive attention for SLR. The designed two attention mechanisms are used to investigate intra-modal and inter-modal correlations of surface Electromyography (sEMG) and inertial measurement unit (IMU) signals, and fuse the two modalities. Statistical attention uses the Laplace operator and lower quantile to select and enhance active features within each modal feature clip. Contrastive attention calculates the information gain of active features in a couple of enhanced feature clips located at the same position in two modalities. The enhanced feature clips are then fused in their positions based on the gain. The fused multimodal features are fed into a Transformer-based network with connectionist temporal classification and cross-entropy losses for SLR. The experimental results show that SeeSign has accuracy of 93.17% for isolated words, and word error rates of 18.34% and 22.08% on one-handed and two-handed sign language datasets, respectively. Moreover, it outperforms state-of-the-art methods in terms of accuracy and robustness.

报告题目：IF-ConvTransformer: A Framework for Human Activity Recognition Using IMU Fusion and ConvTransformer 论坛讲者：张晔，王龙光，陈慧玲，田奥升，周石琳 出处：Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 报告摘要：Recent advances in sensor based human activity recognition (HAR) have exploited deep hybrid networks to improve the performance. These hybrid models combine Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) to leverage their complementary advantages, and achieve impressive results. However, the roles and associations of different sensors in HAR are not fully considered by these models, leading to insufficient multi-modal fusion. Besides, the commonly used RNNs in HAR suffer from the 'forgetting' defect, which raises difficulties in capturing long-term information. To tackle these problems, an HAR framework composed of an Inertial Measurement Unit (IMU) fusion block and an applied ConvTransformer subnet is proposed in this paper. Inspired by the complementary filter, our IMU fusion block performs multi-modal fusion of commonly used sensors according to their physical relationships. Consequently, the features of different modalities can be aggregated more effectively. Then, the extracted features are fed into the applied ConvTransformer subnet for classification. Thanks to its convolutional subnet and self-attention layers, ConvTransformer can better capture local features and construct long-term dependencies. Extensive experiments on eight benchmark datasets demonstrate the superior performance of our framework. The source code will be published soon.

报告题目：ANOMALOUS SOUND DETECTION USING AUDIO REPRESENTATION WITH MACHINE ID BASED CONTRASTIVE LEARNING PRETRAINING 论坛讲者：关键，肖飞扬，柳友德，朱乔茜，王文武 出处：2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 报告摘要：Existing contrastive learning methods for anomalous sound detection refine the audio representation of each audio sample by using the contrast between the samples’ augmentations (e.g., with time or frequency masking). However, they might be biased by the augmented data, due to the lack of physical properties of machine sound, thereby limiting the detection performance. This paper uses contrastive learning to refine audio representations for each machine ID, rather than for each audio sample. The proposed two-stage method uses contrastive learning to pretrain the audio representation model by incorporating machine ID and a self-supervised ID classifier to fine-tune the learnt model, while enhancing the relation between audio features from the same ID. Experiments show that our method outperforms the state-of-the-art methods using contrastive learning or self-supervised classification in overall anomaly detection performance and stability on DCASE 2020 Challenge Task2 dataset.

报告题目：TIME-WEIGHTED FREQUENCY DOMAIN AUDIO REPRESENTATION WITH GMM ESTIMATOR FOR ANOMALOUS SOUND DETECTION 论坛讲者：关键，柳友德，朱乔茜，郑铁然，韩纪庆，王文武 出处：2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 报告摘要：Although deep learning is the mainstream method in unsupervised anomalous sound detection, Gaussian Mixture Model (GMM) with statistical audio frequency representation as input can achieve comparable results with much lower model complexity and fewer parameters. Existing statistical frequency representations, e.g. the log-Mel spectrogram’s average or maximum over time, do not always work well for different machines. This paper presents Time-Weighted Frequency Domain Representation (TWFR) with the GMM method (TWFR-GMM) for anomalous sound detection. The TWFR is a generalized statistical frequency domain representation that can adapt to different machine types, using the global weighted ranking pooling over time-domain. This allows GMM estimator to recognize anomalies, even under domain-shift conditions, as visualized with a Mahalanobis distance-based metric. Experiments on DCASE 2022 Challenge Task2 dataset show that our method has better detection performance than recent deep learning methods. TWFR-GMM is the core of our submission that achieved the 3rd place in DCASE 2022 Challenge Task2.

报告题目：Spatio-temporal Diffusion Point Processes 论坛讲者：Yuan Yuan，Jingtao Ding，Chenyang Shao，Depeng Jin，Yong Li 出处：Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining 2023 报告摘要：Spatio-temporal point process (STPP) is a stochastic collection of events accompanied with time and space. Due to computational complexities, existing solutions for STPPs compromise with conditional independence between time and space, which consider the temporal and spatial distributions separately. The failure to model the joint distribution leads to limited capacities in characterizing the spatio-temporal entangled interactions given past events. In this work, we propose a novel parameterization framework for STPPs, which leverages diffusion models to learn complex spatio-temporal joint distributions. We decompose the learning of the target joint distribution into multiple steps, where each step can be faithfully described by a Gaussian distribution. To enhance the learning of each step, an elaborated spatio-temporal co-attention module is proposed to capture the interdependence between the event time and space adaptively. For the first time, we break the restrictions on spatiotemporal dependencies in existing solutions, and enable a flexible and accurate modeling paradigm for STPPs. Extensive experiments from a wide range of fields, such as epidemiology, seismology, crime, and urban mobility, demonstrate that our framework outperforms the state-of-the-art baselines remarkably. Further in-depth analyses validate its ability to capture spatio-temporal interactions, which can learn adaptively for different scenarios. The datasets and source code are available online: https://github.com/tsinghua-fiblab/Spatio-temporal-Diffusion-Point-Processes

报告题目：Practical Synthetic Human Trajectories Generation Based on Variational Point Processes 论坛讲者：隆青月，王寰东，李桐，黄丽思，王昆，吴琼，李光宇，梁燕萍，余立，李勇 出处：Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining 2023 报告摘要：Human trajectories, reflecting people’s travel patterns and the range of activities, are crucial for the applications like urban planning and epidemic control. However, the real-world human trajectory data tends to be limited by user privacy or device acquisition issues, leading to its insufficient quality to support the above applications. Hence, generating human trajectory data is a crucial but challenging task, which suffers from the following two critical challenges: 1) how to capture the user distribution in human trajectories (group view), and 2) how to model the complex mobility patterns of each user trajectory (individual view). In this paper, we propose a novel human trajectories generator (named VOLUNTEER), consisting of a user VAE and a trajectory VAE, to address the above challenges. Specifically, in the user VAE, we propose to learn the user distribution with all human trajectories from a group view. In the trajectory VAE, from the individual view, we model the complex mobility patterns by decoupling travel time and dwell time to accurately simulate individual trajectories. Extensive experiments on two real-world datasets show the superiority of our model over the state-of-the-art baselines. Further application analysis in the industrial system also demonstrates the effectiveness of our model.

报告题目：Deep Transfer Learning for City-scale Cellular Traffic Generation through Urban Knowledge Graph 论坛讲者：Shiyuan Zhang，Tong Li，Shuodi Hui，Guangyu Li，Yanping Liang，Li Yu，Depeng Jin，Yong Li 出处：Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining 报告摘要：The problem of cellular traffic generation in cities without historical traffic data is critical and urgently needs to be solved to assist 5G base station deployments in mobile networks. In this paper, we propose ADAPTIVE, a deep transfer learning framework for city-scale cellular traffic generation through the urban knowledge graph. ADAPTIVE leverages historical data from other cities that have deployed 5G networks to assist cities that are newly deploying 5G networks through deep transfer learning. Specifically, ADAPTIVE can align the representations of base stations in the target city and source city while considering the environmental factors of cities, spatial and environmental contextual relations between base stations, and traffic temporal patterns at base stations. We next design a feature-enhanced generative adversarial network, which is trained based on the historical traffic data and representations of base stations in the source city. By feeding the aligned target city’s base station representations into the trained model, we can then obtain the generated traffic data for the target city. Extensive experiments on real-world cellular traffic datasets show that ADAPTIVE generally outperforms state-of-the-art baselines by more than 40% in terms of Jensen–Shannon divergence and root-mean-square error. Also, ADAPTIVE has strong robustness based on the results of various cross-city experiments. ADAPTIVE has been successfully deployed on the ‘Jiutian’ Artificial Intelligence Platform of China Mobile to support cellular traffic generation and assist in the construction and operation of mobile networks.

报告题目：Road Planning for Slums via Deep Reinforcement Learning 论坛讲者：郑瑜，苏泓源，丁璟韬，金德鹏，李勇 出处：Conference version of this paper published in KDD'23 报告摘要：Millions of slum dwellers suffer from poor accessibility to urban services due to inadequate road infrastructure within slums, and road planning for slums is critical to the sustainable development of cities. Existing re-blocking or heuristic methods are either timeconsuming which cannot generalize to different slums, or yield sub-optimal road plans in terms of accessibility and construction costs. In this paper, we present a deep reinforcement learning based approach to automatically layout roads for slums. We propose a generic graph model to capture the topological structure of a slum, and devise a novel graph neural network to select locations for the planned roads. Through masked policy optimization, our model can generate road plans that connect places in a slum at minimal construction costs. Extensive experiments on real-world slums in different countries verify the effectiveness of our model, which can significantly improve accessibility by 14.3% against existing baseline methods. Further investigations on transferring across different tasks demonstrate that our model can master road planning skills in simple scenarios and adapt them to much more complicated ones, indicating the potential of applying our model in real-world slum upgrading. The code and data are available at https://github.com/ tsinghua-fib-lab/road-planning-for-slums.

报告题目：Hybrid RSU Deployment in Cybertwin-IoV for Temporal and Spatial Service Coverage 论坛讲者：Yuanzhi Ni, Chengcheng Zhao, Lin Cai 出处：IEEE Transactions on Vehicular Technology 2022 报告摘要：Roadside Unit (RSU) plays an important role in Vehicle-to-Everything (V2X) service on the Internet of Vehicles (IoV). Due to the limitation of the existing network architecture, the RSU management technology either cannot fulfill the time location-varying service demands or consumes a large number of resource to cover the interested area. To mitigate the gap between the stringent V2X requirements and the limited available resource, a cybertwin-based IoV architecture is proposed to facilitate the RSU management and achieve always-on V2X services. Two types of RSUs, i.e., static RSU (sRSU) and mobile RSU (mRSU), are applied in infrastructure-assisted V2X communications. To evaluate the performance of cybertwin-based RSU deployment and scheduling, the utility maximization problem with coverage constraints is formulated. A three-stage hybrid RSU management strategy is proposed considering the different granularity of service loads. First, sRSUs are deployed to satisfy the basic service demands in different areas. Second, mRSUs are flexibly selected and managed to adapt to real-time variations of service loads. Finally, the RSUs are scheduled based on the real-time load prediction. The case study of Wuxi city illustrates that the proposed solution outperforms the existing strategy in terms of the deployment utility, response ratio, and adaptiveness to demand dynamics.

报告题目：Boost Spectrum Prediction With Temporal-Frequency Fusion Network via Transfer Learning 论坛讲者：Kehan Li, Chao Li, Jiming Chen, Qiming Zhang, Zebo Liu, Shibo He 出处：IEEE Transactions on Mobile Computing 2023 报告摘要：Modeling and predicting the radio spectrum is vital for spectrum management, such as spectrum sharing and anomaly detection. Nevertheless, the precise spectrum prediction is challenging due to the interference from both intra-spectrum and external factors. To tackle these complex internal and external correlations, we develop a model named TF 2 AN, consisting of three components: 1) a robust signal detection algorithm based on image processing, 2) an attention-based Long Short-term Memory network to capture the temporal-frequency correlations, 3) a generalized fusion module to take the heterogeneous external factors into account. This structure shows prominent effectiveness for spectrum prediction on a single monitoring station with sufficient data. However, when the data derived from a single station is insufficient, the performance of the deep learning model will decline a lot. Considering that more than one monitoring station is deployed in practice, the new challenge becomes how to enhance our model by leveraging the data from multiple stations or frequency bands. Therefore, we further propose T-TF 2 AN, a transfer learning-based framework for data augmentation and knowledge sharing in spectrum prediction. Compared to TF 2 AN, better performance is achieved. Besides, the model interpretability and training efficiency are also discussed with two case studies, respectively.

报告题目：USAF: Multimodal Chinese Named Entity Recognition Using Synthesized Acoustic Features 论坛讲者：刘野, 黄少滨, 李熔盛, 闫乃玉, 杜治娟 出处：Information Processing & Management 报告摘要：Due to the particularity of Chinese word formation, the Chinese Named Entity Recognition (NER) task has attracted extensive attention over recent years. Recently, some researchers have tried to solve this problem by using a multimodal method combining acoustic features and text features. However, the text-speech data pairs required by the above methods are lacking in real-world scenarios, making it difficult to apply widely. To address this, we proposed a multimodal Chinese NER method called USAF, which uses synthesized acoustic features instead of actual human speech. USAF aligns text and acoustic features through unique position embeddings and uses a multi-head attention mechanism to fuse the features of the two modalities, which stably improves the performance of Chinese named entity recognition. To evaluate USAF, we implemented USAF on three Chinese NER datasets. Experimental results show that USAF witnesses a stable improvement compare to text-only methods on each dataset, and outperforms SOTA external-vocabulary-based method on two datasets. Specifically, compared to the SOTA external-vocabulary-based method, the F1 score of USAF is improved by 1.84 and 1.24 on CNERTA and Aishell3-NER, respectively.

报告题目：SPMA: Stealthy Physics-Manipulated Attack and Countermeasures in Cyber-Physical Smart Grid 论坛讲者：张镇勇, 邓瑞龙, 程鹏, 田有亮, 马建峰 出处：IEEE Transactions on Information Forensics and Security 报告摘要：As a critical infrastructure, the traditional power system has transformed into a cyber-physical integrated smart grid. However, the vulnerabilities exposed in either the cyber or physical layer might be exploited by adversaries to construct complicated and coordinated attacks consequent in destructive impacts. In this paper, we propose a stealthy physics-manipulated attack (SPMA) by masking the physical attacks on the flexible AC transmission system (FACTS) with strategic cyberattacks. To construct the SPMA, we first manipulate the control command sent to the FACTS device to change the reactance and then tamper with the sensor measurements to conceal it. The SPMA is constructed with complete-informed and incomplete-informed attackers, noisy sensor measurements, and a nonlinear AC model, respectively. The impact of the physics manipulation on the real-time economic dispatch and the system’s operation security are formulated and numerically analyzed. Furthermore, we also provide potential countermeasures from three aspects to defend against SPMAs. Finally, extensive experiments are conducted with the IEEE test power systems to evaluate the stealthiness of SPMAs and the economic losses and potential cascading failures caused by SPMAs using real-world load profiles.

报告题目：D-S based Fusion Method for Against Malicious Nodes in Wireless Sensor Networks 论坛讲者：田乔, 秦鹏万, 王美玉, 刘洋 出处：IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) 报告摘要：Malicious nodes attacks pose a great security threat to the multi-sensor networks, especially the fusion result of the fusion center. Dempster-Shafer (D-S) evidence theory is a very effective fusion method, but conflict evidences brought by malicious nodes will greatly affect the accuracy of traditional D-S fusion method. Based on the above considerations, this paper adopts an improved D-S evidence theory method, which can intelligently reduce the influence of malicious nodes on the decide results during the fusion process, thereby improving the security of the entire wireless sensor networks. Finally, several examples are carried out on the background of network security situational awareness, which proves the feasibility of the proposed method.

报告题目：Efficient Revenue-based MEC Server Deployment and Management in Mobile Edge-Cloud Computing 论坛讲者：王威, 张永敏 出处：IEEE/ACM Transactions on Networking ( Early Access ) 报告摘要：With the explosive growth of mobile applications, the development of mobile edge computing (MEC) has been greatly promoted since it can ably improve the quality of service for mobile applications by providing low latency and high-quality computation services. Most existing works focus on improving the efficiency of MEC with an assumption that the MEC servers have already been deployed. However, without appropriate deployment of MEC servers, the profitability of the MEC system can be significantly restrained, which hinders the rapid promotion of the MEC. To address this issue, we formulate an MEC server deployment problem for the MEC operator as a revenue maximization problem. Firstly, we model and analyze the various factors that affect the revenue. Secondly, we formulate a revenue maximization problem, which is NP-hard, but it is proved to be convex with respect to the total available computation units. Based on this feature, we propose a three-layer optimization algorithm, named EDM, in which the location, the deployed computation units, and the wholesaled computation resources are determined gradually, to maximize the total revenue. Experimental results demonstrate that the proposed EDM algorithm has significant advantages on revenue improvement compared to competitive benchmarks.

报告题目：Assessing the Traffic Scheduling Method for Time-sensitive Networking (TSN) by Practical Implementation 论坛讲者：江俊慧, 金善玉 出处：Journal of Industrial Information Integration 报告摘要：Time-sensitive networking (TSN), as standardized and maintained by the IEEE 802.1 Task Group, enhances the real-time and deterministic capabilities of the Ethernet. However, traffic scheduling is not standardized, and is being extensively researched. Most studies are theoretical in nature; practical validation studies are rare. To fill this gap, we first constructed a real-world TSN-based process automation system and presented fine-grained guidelines regarding how a traffic scheduling method (TSM) can be deployed in industrial facilities. We experimentally investigated the feasibility of our method, and compared its performance to that of a commercial TSN scheduler. The results show that our method precisely schedules traffic to satisfy firm real-time requirements and achieves ultra-low latency by eliminating the queuing delays. The scheduling calculation times for 500 random cases show that our TSM can appropriately schedule flows in milliseconds, more than 571-fold faster than the commercial scheduler.

报告题目：Smart Contract Vulnerability Detection Using Graph Neural Networks 论坛讲者：Yuan Zhuan, Zhenguang Liu, Peng Qian, Qi Liu, Xiang Wang, Qinming He 出处：Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI-20) 报告摘要：The security problems of smart contracts have drawn extensive attention due to the enormous financial losses caused by vulnerabilities. Existing methods on smart contract vulnerability detection heavily rely on fixed expert rules, leading to low detection accuracy. In this paper, we explore using graph neural networks (GNNs) for smart contract vulnerability detection. Particularly, we construct a contract graph to represent both syntactic and semantic structures of a smart contract function. To highlight the major nodes, we design an elimination phase to normalize the graph. Then, we propose a degree-free graph convolutional neural network (DR-GCN) and a novel temporal message propagation network (TMP) to learn from the normalized graphs for vulnerability detection. Extensive experiments show that our proposed approach significantly outperforms state-of-the-art methods in detecting three different types of vulnerabilities.